Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/actions/windows-setup-cuda/action.yml
#	.github/workflows/release.yml
#	.github/workflows/server-sanitize.yml
#	models/templates/poolside-Laguna-S-2.1.jinja
#	scripts/sync_vendor.py
#	tests/test-backend-ops.cpp
#	tests/test-chat-auto-parser.cpp
#	tests/test-llama-archs.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md

cmake/arm64-windows-msvc-cuda.cmake

@@ -0,0 +1,26 @@
+# Used to cross-compile ggml-cuda for Windows ARM64 on an x64 Windows host.
+set( CMAKE_SYSTEM_NAME Windows )
+set( CMAKE_SYSTEM_PROCESSOR arm64 )
+
+if ( DEFINED CUDAToolkit_ROOT )
+    file( TO_CMAKE_PATH "${CUDAToolkit_ROOT}" CUDA_ROOT )
+elseif ( DEFINED ENV{CUDA_PATH} )
+    file( TO_CMAKE_PATH "$ENV{CUDA_PATH}" CUDA_ROOT )
+else()
+    message( FATAL_ERROR "Set CUDAToolkit_ROOT or CUDA_PATH to a Windows CUDA Toolkit with ARM64 target libraries" )
+endif()
+
+if ( DEFINED ENV{VCToolsInstallDir} )
+    file( TO_CMAKE_PATH "$ENV{VCToolsInstallDir}" MSVC_TOOLS_ROOT )
+    set( CMAKE_CUDA_HOST_COMPILER "${MSVC_TOOLS_ROOT}/bin/Hostx64/arm64/cl.exe" CACHE FILEPATH "" )
+endif()
+
+set( CMAKE_CUDA_COMPILER "${CUDA_ROOT}/bin/nvcc.exe" CACHE FILEPATH "" )
+set( CMAKE_CUDA_FLAGS_INIT "-target-dir=arm64" )
+
+# FindCUDAToolkit selects lib/x64 from the host architecture on Windows.
+set( CUDA_CUDART              "${CUDA_ROOT}/lib/arm64/cudart.lib"   CACHE FILEPATH "" )
+set( CUDA_cudart_LIBRARY      "${CUDA_ROOT}/lib/arm64/cudart.lib"   CACHE FILEPATH "" )
+set( CUDA_cublas_LIBRARY      "${CUDA_ROOT}/lib/arm64/cublas.lib"   CACHE FILEPATH "" )
+set( CUDA_cublasLt_LIBRARY    "${CUDA_ROOT}/lib/arm64/cublasLt.lib" CACHE FILEPATH "" )
+set( CUDA_cuda_driver_LIBRARY "${CUDA_ROOT}/lib/arm64/cuda.lib"     CACHE FILEPATH "" )

common/arg.cpp

@@ -3313,8 +3313,9 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         {"--tools-runtime"}, "OPTION",
         "experimental: run tools in a separate runtime environment (default: none, use host environment)\n"
         "available options:\n"
-        "  'docker:<image>': spin up a new Docker container and reuse it for all invocations, clean up on server exit\n"
-        "  'docker-container:<id>': use an existing Docker container by ID, won't stop on server exit\n",
+        "  'docker:<image>', 'podman:<image>': spin up a new container and reuse it for all invocations, clean up on server exit\n"
+        "  'docker-container:<id>', 'podman-container:<id>': use an existing container by ID, won't stop on server exit\n"
+        "  'ssh:<target>': run tools on a remote POSIX host over SSH, key-based auth and a trusted host key are required\n",
         [](common_params & params, const std::string & value) {
             params.server_tools_runtime = value;
         }

common/chat.cpp

@@ -3100,6 +3100,151 @@ static common_chat_params common_chat_params_init_minicpm5(const common_chat_tem
     return data;
 }
 
+// An assistant turn is rendered as one or more messages, each
+// "<|start|>assistant to=<recipient><|message|>{content}{END}" where END is
+// <|eom|> (more messages follow) or <|eot|> (end of turn):
+//   - chain-of-thought: to=self, terminated by <|eom|>
+//   - final answer:     to=user, terminated by <|eot|>
+// The generation prompt is just "<|start|>assistant"; the model emits its own
+// " to=...<|message|>".
+static common_chat_params common_chat_params_init_muse_glimmer(const common_chat_template &          tmpl,
+                                                               const autoparser::generation_params & inputs) {
+    common_chat_params data;
+
+    data.prompt            = common_chat_template_direct_apply_impl(tmpl, inputs);
+    data.generation_prompt = "<|start|>assistant";
+    data.format            = COMMON_CHAT_FORMAT_PEG_NATIVE;
+    data.supports_thinking = true;
+
+    data.preserved_tokens = {
+        "<|start|>", "<|message|>", "<|eom|>", "<|eot|>",
+        // ATEM tool-call markup emitted on " to=<tool>" turns.
+        "<atem:function_calls>", "<atem:invoke", "<atem:parameter", "</atem:parameter>",
+        "</atem:invoke>", "</atem:function_calls>",
+    };
+
+    data.message_delimiters = {
+        { COMMON_CHAT_ROLE_ASSISTANT, "<|start|>assistant" },
+        { COMMON_CHAT_ROLE_USER,      "<|start|>user"      },
+        { COMMON_CHAT_ROLE_SYSTEM,    "<|start|>system"    },
+        { COMMON_CHAT_ROLE_TOOL,      "<|start|>tool"      },
+    };
+
+    if (inputs.has_continuation()) {
+        const auto & msg = inputs.continue_msg;
+
+        data.generation_prompt = "<|start|>assistant to=self<|message|>" + msg.reasoning_content;
+        if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) {
+            data.generation_prompt += "<|eom|><|start|>assistant to=user<|message|>" + msg.render_content();
+        }
+
+        data.prompt += data.generation_prompt;
+    }
+
+    auto extract_reasoning = inputs.reasoning_format != COMMON_REASONING_FORMAT_NONE;
+
+    auto has_tools = inputs.tools.is_array() && !inputs.tools.empty();
+    // Constrained grammar whenever tools are offered.
+    auto include_grammar = has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE;
+
+    auto parser = build_chat_peg_parser([&](common_chat_peg_builder & p) {
+        auto start = p.rule("start", p.literal("<|start|>assistant"));
+
+        if (!extract_reasoning && !include_grammar) {
+            return start + p.content(p.rest());
+        }
+
+        if (extract_reasoning) {
+            p.rule("analysis", p.literal(" to=self<|message|>") + p.reasoning(p.until("<|eom|>")) + p.literal("<|eom|>"));
+        } else {
+            p.rule("analysis", p.literal(" to=self<|message|>") + p.content(p.until("<|eom|>")) + p.literal("<|eom|>"));
+        }
+        auto analysis = p.ref("analysis");
+
+        auto recipient  = p.optional(p.literal(" to=user"));
+        auto final_msg  = p.rule("final", recipient + p.literal("<|message|>") + p.content(p.until("<|eot|>")));
+
+        if (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE) {
+            auto string_value = p.ac(
+                p.tool_arg_string_value(p.until("</atem:parameter>")) + p.tool_arg_close(p.literal("</atem:parameter>")),
+                "</atem:parameter>");
+
+            auto tool_choice = p.choice();
+            foreach_function(inputs.tools, [&](const json & tool) {
+                const auto &      function = tool.at("function");
+                const std::string name     = function.at("name");
+                auto              params   = function.contains("parameters") ? function.at("parameters") : json::object();
+
+                auto args = p.eps();
+                if (params.contains("properties") && params.at("properties").is_object() && !params.at("properties").empty()) {
+                    auto schema_info = common_schema_info();
+                    schema_info.resolve_refs(params);
+
+                    auto arg_choice = p.choice();
+                    for (const auto & [prop_name, prop_schema] : params.at("properties").items()) {
+                        auto value_parser = p.eps();
+                        if (schema_info.resolves_to_string(prop_schema)) {
+                            value_parser = string_value;
+                        } else {
+                            value_parser = p.tool_arg_json_value(
+                                    p.schema(p.json(), "tool-" + name + "-arg-" + prop_name + "-schema", prop_schema, false))
+                                + p.tool_arg_close(p.literal("</atem:parameter>"));
+                        }
+
+                        auto arg_rule = p.tool_arg(
+                            p.tool_arg_open(p.literal("<atem:parameter name=\"") + p.tool_arg_name(p.literal(prop_name)) + p.literal("\">")) +
+                            value_parser);
+
+                        arg_choice |= arg_rule;
+                    }
+                    args = p.zero_or_more(arg_choice + p.space());
+                }
+
+                auto tool_parser = p.tool(
+                    p.tool_open(p.literal(" to=") + p.until("<|message|>") +
+                                p.literal("<|message|><atem:function_calls>") + p.space() +
+                                p.literal("<atem:invoke name=\"") + p.tool_name(p.literal(name)) + p.literal("\">") + p.space())
+                    << p.tool_args(args)
+                    << p.tool_close(p.literal("</atem:invoke>") + p.space() + p.literal("</atem:function_calls>")));
+
+                tool_choice |= p.rule("tool-" + name, tool_parser);
+            });
+
+            auto tool_calls = inputs.parallel_tool_calls
+                ? p.trigger_rule("tool-call", tool_choice + p.zero_or_more(p.literal("<|eom|>") + start + tool_choice))
+                : p.trigger_rule("tool-call", tool_choice);
+
+
+            if (inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED) {
+                return p.zero_or_more(start + analysis) + start + tool_calls;
+            }
+            return p.zero_or_more(start + analysis) + start + (tool_calls | final_msg);
+        }
+
+        return p.zero_or_more(start + analysis) + start + final_msg;
+    });
+
+    data.parser = parser.save();
+
+    if (include_grammar) {
+        data.grammar_lazy = inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_REQUIRED;
+        data.grammar      = build_grammar([&](const common_grammar_builder & builder) {
+            foreach_function(inputs.tools, [&](const json & tool) {
+                const auto & function = tool.at("function");
+                auto         schema   = function.contains("parameters") ? function.at("parameters") : json::object();
+                builder.resolve_refs(schema);
+            });
+            parser.build_grammar(builder, data.grammar_lazy);
+        });
+        data.grammar_triggers = {
+            { COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN,
+              "<\\|start\\|>assistant( to=(?!self<\\|message\\|>)(?!user<\\|message\\|>)[^<]*?<\\|message\\|>)" },
+        };
+    }
+
+    return data;
+}
+
 static json common_chat_extra_context() {
     json ctx = json::object();
     std::chrono::system_clock::time_point now = std::chrono::system_clock::now();
@@ -3128,6 +3273,12 @@ std::optional<common_chat_params> common_chat_try_specialized_template(
         return common_chat_params_init_gpt_oss(tmpl, params);
     }
 
+    // Muse Glimmer format using " to=<recipient>" recipients and <|eom|>/<|eot|> message terminators.
+    if (src.find("<atem:function_calls>") != std::string::npos && src.find("<|eom|>") != std::string::npos) {
+        LOG_DBG("Using specialized template: Muse Glimmer\n");
+        return common_chat_params_init_muse_glimmer(tmpl, params);
+    }
+
     // Functionary v3.2 - uses recipient-based format with >>>recipient\n{content}
     // Detection: template has ">>>all" for content and ">>>" prefix for tool calls
     if (src.find(">>>all") != std::string::npos && src.find(">>>${recipient}") != std::string::npos) {

common/speculative.cpp

@@ -1032,7 +1032,14 @@ struct common_speculative_impl_draft_dflash : public common_speculative_impl {
             return true;
         }
 
-        if (batch_in.token == nullptr || batch_in.embd != nullptr) {
+        // Target prefill may contain token IDs or multimodal embeddings. Both
+        // produce the target-layer features used to seed the draft KV cache, so
+        // skipping the embedding batches leaves a hole in the draft's cache and
+        // the next injection fails to initialize.
+        // TODO: revisit after https://github.com/ggml-org/llama.cpp/pull/24669 is merged
+        const bool has_tokens     = batch_in.token != nullptr;
+        const bool has_embeddings = batch_in.embd  != nullptr;
+        if (has_tokens == has_embeddings) {
             return true;
         }
 

conversion/__init__.py

@@ -183,6 +183,8 @@ TEXT_MODEL_MAP: dict[str, str] = {
     "Olmo3ForCausalLM": "olmo",
     "OlmoForCausalLM": "olmo",
     "OlmoeForCausalLM": "olmo",
+    "MuseGlimmerAssistantModel": "muse_glimmer",
+    "MuseGlimmerForConditionalGeneration": "muse_glimmer",
     "OpenELMForCausalLM": "openelm",
     "OrionForCausalLM": "orion",
     "PLMForCausalLM": "plm",
@@ -298,6 +300,7 @@ MMPROJ_MODEL_MAP: dict[str, str] = {
     "MiniCPMV4_6ForConditionalGeneration": "minicpm",
     "Mistral3ForConditionalGeneration": "llava",
     "NemotronH_Nano_VL_V2": "nemotron",
+    "MuseGlimmerForConditionalGeneration": "muse_glimmer",
     "PaddleOCRVisionModel": "ernie",
     "Phi4ForCausalLMV": "phi",
     "Qwen2AudioForConditionalGeneration": "ultravox",

conversion/muse_glimmer.py

@@ -0,0 +1,179 @@
+from __future__ import annotations
+
+import json
+from typing import Any, Iterable, TYPE_CHECKING
+
+import torch
+
+if TYPE_CHECKING:
+    from torch import Tensor
+
+from .base import MmprojModel, ModelBase, TextModel, gguf
+
+
+def _unpermute_for_rope(tensor: "Tensor", n_heads: int) -> "Tensor":
+    """Invert transformers' `_permute_for_rope`: HF stores Q/K in rotate_half layout,
+    llama.cpp consumes the interleaved (NORM) layout."""
+    if tensor.ndim == 2:
+        dim1, dim2 = tensor.shape
+        return tensor.view(n_heads, 2, dim1 // n_heads // 2, dim2).transpose(1, 2).reshape(dim1, dim2)
+    if tensor.ndim == 1:
+        (dim1,) = tensor.shape
+        return tensor.view(n_heads, 2, dim1 // n_heads // 2).transpose(1, 2).reshape(dim1)
+    raise ValueError(f"_unpermute_for_rope: unexpected shape {tuple(tensor.shape)}")
+
+
+@ModelBase.register("MuseGlimmerForConditionalGeneration")
+class MuseGlimmerModel(TextModel):
+    model_arch = gguf.MODEL_ARCH.MUSE_GLIMMER
+
+    def norm_shift(self, name: str) -> float:
+        # All four layer norms use 1, the final norm uses 0.
+        return 1.0 if name.endswith("layernorm.weight") else 0.0
+
+    def set_vocab(self):
+        self._set_vocab_gpt2()
+
+        from transformers import AutoTokenizer
+        tok = AutoTokenizer.from_pretrained(self.dir_model)
+        eot_id = tok.convert_tokens_to_ids("<|eot|>")
+        if isinstance(eot_id, int) and eot_id >= 0:
+            self.gguf_writer.add_eot_token_id(eot_id)
+
+    def set_gguf_parameters(self):
+        super().set_gguf_parameters()
+        hparams = self.hparams
+
+        self.gguf_writer.add_final_logit_softcapping(hparams["final_logit_softcapping"])
+        self.gguf_writer.add_logit_scale(hparams["output_multiplier"])
+        self.gguf_writer.add_sliding_window(hparams["sliding_window"])
+        self.gguf_writer.add_sliding_window_pattern([t == "sliding_attention" for t in hparams["layer_types"]])
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        shift = self.norm_shift(name)
+        if shift != 0.0:
+            data_torch = data_torch + shift
+
+        # Invert transformers' `_permute_for_rope` on Q/K, we keep ggml's NORM (interleaved) rope
+        if ".self_attn.q_proj." in name:
+            data_torch = _unpermute_for_rope(data_torch, int(self.hparams["num_attention_heads"]))
+        elif ".self_attn.k_proj." in name:
+            data_torch = _unpermute_for_rope(data_torch, int(self.hparams["num_key_value_heads"]))
+
+        # Synthesize QK-norm weights to absorb qk_scale_factor.
+        # MuseGlimmer implementation: scaleless RMSNorm followed by qk_scale_factor..
+        if bid is not None and name.endswith(f"model.layers.{bid}.self_attn.q_proj.weight"):
+            head_dim = self.hparams["head_dim"]
+            q_scale = float(self.hparams["qk_scale_factor"])
+            yield (
+                self.map_tensor_name(f"model.layers.{bid}.self_attn.q_norm.weight"),
+                torch.full((head_dim,), q_scale, dtype=torch.float32),
+            )
+            yield (
+                self.map_tensor_name(f"model.layers.{bid}.self_attn.k_norm.weight"),
+                torch.ones((head_dim,), dtype=torch.float32),
+            )
+
+        yield from super().modify_tensors(data_torch, name, bid)
+
+
+@ModelBase.register("MuseGlimmerForConditionalGeneration")
+class MuseGlimmerVisionModel(MmprojModel):
+    def get_vision_config(self) -> dict[str, Any] | None:
+        c = self.global_config.get("vision_config")
+        if not c:
+            return None
+        # MuseGlimmer actually uses dynamic size, initialize with nominal size
+        image_size = c["pos_emb_height"] * c["patch_size"] * c["merge_size"]
+        return {**c, "image_size": image_size}
+
+    def set_gguf_parameters(self):
+        super().set_gguf_parameters()
+        assert self.hparams_vision is not None
+        c = self.hparams_vision  # enriched vision_config from get_vision_config()
+
+        self.gguf_writer.add_clip_projector_type(gguf.VisionProjectorType.MUSE_GLIMMER)
+        self.gguf_writer.add_vision_attention_layernorm_eps(float(c["layer_norm_eps"]))
+        self.gguf_writer.add_vision_spatial_merge_size(int(c["merge_size"]))
+
+    @classmethod
+    def filter_tensors(cls, item):
+        name, gen = item
+        keep = ("model.vision_tower.", "model.vision_adapter.", "model.vision_projection.")
+        if not any(name.startswith(k) for k in keep):
+            return None
+        return super().filter_tensors((name, gen))
+
+    # 3-layer projector MLP
+    _MM_MLP_MAP = {
+        "model.vision_adapter.fc1": (gguf.MODEL_TENSOR.V_MMPROJ, 0),
+        "model.vision_adapter.fc2": (gguf.MODEL_TENSOR.V_MMPROJ, 1),
+        "model.vision_projection":  (gguf.MODEL_TENSOR.V_MMPROJ, 2),
+    }
+
+    def modify_tensors(self, data_torch, name, bid):
+        assert self.hparams_vision is not None
+        if ".attn.q_proj." in name or ".attn.k_proj." in name:
+            n_heads = int(self.hparams_vision["num_attention_heads"])
+            data_torch = _unpermute_for_rope(data_torch, n_heads)
+        # Lay out the pt=2 temporal slabs of the patch embedding as a conv2d for build_inp()
+        if name.endswith("patch_embedder.patch_embedding.weight"):
+            n_embd = data_torch.shape[0]
+            pt = int(self.hparams_vision["patch_temporal"])
+            ps = int(self.hparams_vision["patch_size"])
+            data_torch = data_torch.view(n_embd, pt, 3, ps, ps).sum(dim=1)  # (n_embd, 3, ps, ps)
+        stem, _, suffix = name.rpartition(".")
+        if stem in self._MM_MLP_MAP:
+            tensor_key, idx = self._MM_MLP_MAP[stem]
+            yield (self.format_tensor_name(tensor_key, bid=idx, suffix="." + suffix), data_torch)
+            return
+        yield (self.map_tensor_name(name), data_torch)
+
+
+@ModelBase.register("MuseGlimmerAssistantModel")
+class MuseGlimmerAssistantModel(TextModel):
+    model_arch = gguf.MODEL_ARCH.DFLASH
+
+    def set_vocab(self):
+        if self.target_model_dir is None:
+            raise ValueError(
+                "MuseGlimmerAssistant (DFlash drafter) requires --target-model-dir pointing to the "
+                "target MuseGlimmer HF directory"
+            )
+
+        original_dir = self.dir_model
+        self.dir_model = self.target_model_dir
+
+        from . import get_model_class
+        with open(self.target_model_dir / "config.json", "r", encoding="utf-8") as f:
+            target_arch = json.load(f)["architectures"][0]
+        target_cls = get_model_class(target_arch)
+        if target_cls is not type(self):
+            target_cls.set_vocab(self)  # ty: ignore[unresolved-attribute]
+        else:
+            super().set_vocab()
+
+        self.dir_model = original_dir
+
+        mask_token_id = self.hparams.get("mask_token_id")
+        if mask_token_id is not None:
+            self.gguf_writer.add_mask_token_id(int(mask_token_id))
+
+    def set_gguf_parameters(self):
+        super().set_gguf_parameters()
+        h = self.hparams
+
+        self.gguf_writer.add_block_size(int(h["block_size"]))
+
+        # dflash.target_layers[k] refers to the inputs going into the ith layer, which come from the (i-1)th layer's output.
+        # The transformers configuration refers to the outputs being recorded.
+        self.gguf_writer.add_target_layers([int(x) + 1 for x in h["target_layer_ids"]])
+
+        if h.get("sliding_window") and h.get("layer_types"):
+            self.gguf_writer.add_sliding_window(int(h["sliding_window"]))
+            self.gguf_writer.add_sliding_window_pattern([t == "sliding_attention" for t in h["layer_types"]])
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        # DFlash defaults to NEOX (rotate_half) rope, matching transformers HF layout for Q/K, QK-norms
+        # no permutation needed.
+        yield (self.map_tensor_name(name), data_torch)

conversion/nemotron.py

@@ -197,6 +197,7 @@ class NemotronHModel(GraniteHybridModel):
     """Hybrid mamba2/attention model from NVIDIA"""
     model_arch = gguf.MODEL_ARCH.NEMOTRON_H
     is_moe: bool = False
+    supports_mtp_export = True
 
     def __init__(self, *args, **kwargs):
         # We have to determine the correct model architecture (MoE vs non-MoE) before
@@ -236,6 +237,25 @@ class NemotronHModel(GraniteHybridModel):
             self._ssm_layers = [i for i, val in enumerate(pattern) if val == "mamba"]
             self._mlp_layers = [i for i, val in enumerate(pattern) if val == "moe"]
 
+        # `--no-mtp` drops it entirely; `--mtp` exports only the MTP head
+        self._mtp_bid: int | None = None
+        if self.is_moe and not self.no_mtp:
+            n_nextn = self.hparams.get("num_nextn_predict_layers", 0) or 0
+            if n_nextn > 0:
+                assert n_nextn == 1, (
+                    "NemotronH MTP conversion currently supports num_nextn_predict_layers == 1"
+                )
+                self._mtp_bid = self.block_count
+                self.block_count += 1
+                # The folded MTP block carries both an attention sub-layer and a
+                # MoE sub-layer, so register it as both so the per-layer metadata arrays cover it
+                self._attn_layers.append(self._mtp_bid)
+                self._mlp_layers.append(self._mtp_bid)
+                self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count)
+
+        if self.mtp_only and self._mtp_bid is None:
+            raise ValueError("--mtp was requested, but this model does not contain a supported MTP head")
+
     def get_attn_layers(self):
         pattern = self.hparams.get("hybrid_override_pattern") or self.hparams.get("layers_block_type")
         if pattern is None:
@@ -246,6 +266,36 @@ class NemotronHModel(GraniteHybridModel):
 
         return [i for i, val in enumerate(pattern) if val == "attention"]
 
+    @classmethod
+    def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None:
+        name, gen = item
+        if name.startswith("mtp."):
+            # --no-mtp: drop the MTP head entirely
+            if cls.no_mtp:
+                return None
+        elif cls.mtp_only:
+            # --mtp: export the MTP head plus the tensors it shares with the target model
+            keep = name in (
+                "backbone.embeddings.weight",
+                "backbone.norm_f.weight",
+                "lm_head.weight",
+            )
+            if not keep:
+                return None
+        return super().filter_tensors((name, gen))
+
+    def prepare_metadata(self, vocab_only: bool):
+        from_dir = self.fname_out.is_dir()
+        super().prepare_metadata(vocab_only=vocab_only)
+
+        if not self.mtp_only or not from_dir:
+            return
+        output_type: str = self.ftype.name.partition("_")[2]
+        fname_default: str = gguf.naming_convention(
+            self.metadata.name, self.metadata.basename, self.metadata.finetune,
+            self.metadata.version, size_label=None, output_type=output_type, model_type=None)
+        self.fname_out = self.fname_out.parent / f"mtp-{fname_default}.gguf"
+
     def set_gguf_parameters(self):
         super().set_gguf_parameters()
 
@@ -284,6 +334,10 @@ class NemotronHModel(GraniteHybridModel):
             if (latent_size := self.hparams.get("moe_latent_size")) is not None:
                 self.gguf_writer.add_moe_latent_size(latent_size)
 
+        # MTP head: number of trailing NextN blocks
+        if self._mtp_bid is not None:
+            self.gguf_writer.add_nextn_predict_layers(self.hparams["num_nextn_predict_layers"])
+
     def set_vocab(self):
         # The NemotronH config uses pattern characters (e.g. '-') that may not
         # be supported by the installed transformers version. AutoTokenizer
@@ -350,15 +404,24 @@ class NemotronHModel(GraniteHybridModel):
         if not self.is_moe:
             self.gguf_writer.add_add_bos_token(True)
 
-    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
-        if self.is_moe and bid is not None:
-            # Skip Multi-Token Prediction (MTP) tensors. These are used for
-            # for speculative decoding but we don't include them in this model
-            # conversion. See https://github.com/ggml-org/llama.cpp/pull/18886
-            if name.startswith("mtp."):
-                logger.info(f"gguf: Skipping MTP (Speculative) layer: {name}")
-                return
+    _MTP_SPECIAL_RENAMES = {
+        "mtp.layers.0.enorm.weight":           "model.layers.{bid}.enorm.weight",
+        "mtp.layers.0.hnorm.weight":           "model.layers.{bid}.hnorm.weight",
+        "mtp.layers.0.eh_proj.weight":         "model.layers.{bid}.eh_proj.weight",
+        "mtp.layers.1.norm.weight":            "model.layers.{bid}.post_attention_layernorm.weight",
+        "mtp.layers.1.final_layernorm.weight": "model.layers.{bid}.shared_head.norm.weight",
+    }
 
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        #   mtp.layers.0: NextN input fusion + attention
+        #   mtp.layers.1: MoE + final head norm
+        if self._mtp_bid is not None and name.startswith(("mtp.layers.0.", "mtp.layers.1.")):
+            suffix = name.split(".", 3)[3]
+            bid = self._mtp_bid
+            renamed = self._MTP_SPECIAL_RENAMES.get(name)
+            name = renamed.format(bid=bid) if renamed else f"backbone.layers.{bid}.{suffix}"
+
+        if self.is_moe and bid is not None:
             if name.endswith("mixer.gate.e_score_correction.bias"):
                 yield from ModelBase.modify_tensors(self, data_torch, name, bid)
                 return

ggml/src/ggml-cpu/ggml-cpu.c

@@ -3443,7 +3443,7 @@ static bool ggml_thread_apply_priority(int32_t prio) {
     return true;
 }
 
-#elif defined(__gnu_linux__)
+#elif defined(__linux__)
 // TODO: this may not work on BSD, to be verified
 
 static bool ggml_thread_apply_affinity(const bool * mask) {

ggml/src/ggml-cuda/ggml-cuda.cu

@@ -5198,7 +5198,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
             return max_bias == 0.0f;
         }
         case GGML_OP_ROLL:
-            if(op->src[0]->type == GGML_TYPE_F32) {
+            if(op->src[0]->type == GGML_TYPE_F32 && ggml_is_contiguous(op->src[0])) {
                 return true;
             }
             return false;

ggml/src/ggml-metal/ggml-metal-device.m

@@ -1274,8 +1274,9 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te
         case GGML_OP_ARGSORT:
         case GGML_OP_TOP_K:
         case GGML_OP_ARANGE:
-        case GGML_OP_ROLL:
             return true;
+        case GGML_OP_ROLL:
+            return ggml_is_contiguous(op->src[0]);
         case GGML_OP_FLASH_ATTN_EXT:
             // for new head sizes, add checks here
             if (op->src[0]->ne[0] != 32 &&

gguf-py/gguf/constants.py

@@ -509,6 +509,7 @@ class MODEL_ARCH(IntEnum):
     OLMO             = auto()
     OLMO2            = auto()
     OLMOE            = auto()
+    MUSE_GLIMMER     = auto()
     OPENELM          = auto()
     ARCTIC           = auto()
     DEEPSEEK         = auto()
@@ -1181,6 +1182,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
     MODEL_ARCH.OLMO:             "olmo",
     MODEL_ARCH.OLMO2:            "olmo2",
     MODEL_ARCH.OLMOE:            "olmoe",
+    MODEL_ARCH.MUSE_GLIMMER:     "muse-glimmer",
     MODEL_ARCH.OPENELM:          "openelm",
     MODEL_ARCH.ARCTIC:           "arctic",
     MODEL_ARCH.DEEPSEEK:         "deepseek",
@@ -1562,8 +1564,8 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
     MODEL_TENSOR.V_MM_UP:                   "mm.up",
     MODEL_TENSOR.V_MM_DOWN:                 "mm.down",
     MODEL_TENSOR.V_MM_GATE:                 "mm.gate",
-    MODEL_TENSOR.V_MM_MERGER_FC1:            "mm.merger.fc1",
-    MODEL_TENSOR.V_MM_MERGER_FC2:            "mm.merger.fc2",
+    MODEL_TENSOR.V_MM_MERGER_FC1:           "mm.merger.fc1",
+    MODEL_TENSOR.V_MM_MERGER_FC2:           "mm.merger.fc2",
     MODEL_TENSOR.V_TOK_BOI:                 "v.boi",
     MODEL_TENSOR.V_TOK_EOI:                 "v.eoi",
     MODEL_TENSOR.V_MM_PRE_NORM:             "mm.pre_norm",
@@ -3331,6 +3333,25 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.FFN_UP_EXP,
         MODEL_TENSOR.FFN_DOWN_EXP,
     ],
+    MODEL_ARCH.MUSE_GLIMMER: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.ATTN_Q,
+        MODEL_TENSOR.ATTN_Q_NORM,
+        MODEL_TENSOR.ATTN_K,
+        MODEL_TENSOR.ATTN_K_NORM,
+        MODEL_TENSOR.ATTN_V,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.ATTN_GATE,
+        MODEL_TENSOR.FFN_GATE,
+        MODEL_TENSOR.FFN_DOWN,
+        MODEL_TENSOR.FFN_UP,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_POST_NORM,
+        MODEL_TENSOR.FFN_PRE_NORM,
+        MODEL_TENSOR.FFN_POST_NORM,
+    ],
     MODEL_ARCH.OPENELM: [
         MODEL_TENSOR.TOKEN_EMBD,
         MODEL_TENSOR.OUTPUT_NORM,
@@ -3846,6 +3867,12 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.FFN_DOWN_SHEXP,
         MODEL_TENSOR.FFN_UP_SHEXP,
         MODEL_TENSOR.FFN_EXP_PROBS_B,
+        # NextN/MTP (draft head)
+        MODEL_TENSOR.ATTN_POST_NORM,
+        MODEL_TENSOR.NEXTN_EH_PROJ,
+        MODEL_TENSOR.NEXTN_ENORM,
+        MODEL_TENSOR.NEXTN_HNORM,
+        MODEL_TENSOR.NEXTN_SHARED_HEAD_NORM,
     ],
     MODEL_ARCH.EXAONE: [
         MODEL_TENSOR.TOKEN_EMBD,
@@ -5160,6 +5187,7 @@ class VisionProjectorType:
     MIMOVL         = "mimovl"
     MIMO_AUDIO     = "mimo_audio"
     GRANITE4_VISION = "granite4_vision"
+    MUSE_GLIMMER   = "muse-glimmer"
 
 
 # Items here are (block size, type size)

gguf-py/gguf/tensor_mapping.py

@@ -382,7 +382,7 @@ class TensorNameMap:
         ),
 
         MODEL_TENSOR.ATTN_GATE: (
-            "model.layers.{bid}.self_attn.gate_proj", # afmoe
+            "model.layers.{bid}.self_attn.gate_proj", # afmoe muse-glimmer
             "model.layers.{bid}.linear_attn.in_proj_z",  # qwen3.5
             "model.layers.{bid}.self_attn.g_proj",    # step3.5 head-wise attention gate
         ),
@@ -1298,10 +1298,12 @@ class TensorNameMap:
             "encoder.final_layer_norm", # t5
             "layer_norm",               # neobert
             "model.hidden_norm",        # dflash
+            "encoder.output_norm_enc",  # dflash (transformers MuseGlimmerAssistant)
         ),
 
         MODEL_TENSOR.FC: (
-            "model.fc", # dflash
+            "model.fc",   # dflash
+            "encoder.fc", # dflash (transformers MuseGlimmerAssistant)
         ),
 
         MODEL_TENSOR.DSPARK_MARKOV_W1: (
@@ -1467,6 +1469,7 @@ class TensorNameMap:
             "vision_tower.patch_embed.patchifier.proj", # dots.ocr
             "vision_model.conv1", # Step3-VL
             "model.vision_embedder.patch_dense", # gemma4 unified
+            "model.vision_tower.patch_embedder.patch_embedding", # muse-glimmer
         ),
 
         MODEL_TENSOR.V_ENC_EMBD_NORM: (
@@ -1534,7 +1537,8 @@ class TensorNameMap:
             "siglip2.vision_model.encoder.layers.{bid}.self_attn.q_proj", # youtuvl
             "model.vision_model.transformer.layers.{bid}.self_attn.q_proj", # Deepseek-OCR CLIP, generated
             "vision_model.model.layers.{bid}.self_attn.q_proj.linear", # gemma4
-            "model.qwen2_model.model.model.layers.{bid}.self_attn.q_proj" # Deepseek-OCR-2 qwen2
+            "model.qwen2_model.model.model.layers.{bid}.self_attn.q_proj", # Deepseek-OCR-2 qwen2
+            "model.vision_tower.layers.{bid}.attn.q_proj", # muse-glimmer
         ),
 
         MODEL_TENSOR.V_ENC_ATTN_Q_NORM: (
@@ -1560,7 +1564,8 @@ class TensorNameMap:
             "model.vision_model.transformer.layers.{bid}.self_attn.k_proj", # Deepseek-OCR CLIP, generated
             "siglip2.vision_model.encoder.layers.{bid}.self_attn.k_proj",
             "vision_model.model.layers.{bid}.self_attn.k_proj.linear", # gemma4
-            "model.qwen2_model.model.model.layers.{bid}.self_attn.k_proj" # Deepseek-OCR-2 qwen2
+            "model.qwen2_model.model.model.layers.{bid}.self_attn.k_proj", # Deepseek-OCR-2 qwen2
+            "model.vision_tower.layers.{bid}.attn.k_proj", # muse-glimmer
         ),
 
         MODEL_TENSOR.V_ENC_ATTN_K_NORM: (
@@ -1586,7 +1591,8 @@ class TensorNameMap:
             "siglip2.vision_model.encoder.layers.{bid}.self_attn.v_proj",
             "model.vision_model.transformer.layers.{bid}.self_attn.v_proj", # Deepseek-OCR CLIP, generated
             "vision_model.model.layers.{bid}.self_attn.v_proj.linear", # gemma4
-            "model.qwen2_model.model.model.layers.{bid}.self_attn.v_proj" # Deepseek-OCR-2 qwen2
+            "model.qwen2_model.model.model.layers.{bid}.self_attn.v_proj", # Deepseek-OCR-2 qwen2
+            "model.vision_tower.layers.{bid}.attn.v_proj", # muse-glimmer
         ),
 
         MODEL_TENSOR.V_ENC_INPUT_NORM: (
@@ -1610,6 +1616,7 @@ class TensorNameMap:
             "vision_tower.blocks.{bid}.norm1", # dots.ocr
             "vision_model.transformer.resblocks.{bid}.ln_1", # Step3-VL
             "model.qwen2_model.model.model.layers.{bid}.input_layernorm", # Deepseek-OCR-2 qwen2
+            "model.vision_tower.layers.{bid}.norm1", # muse-glimmer
         ),
 
         MODEL_TENSOR.V_ENC_ATTN_O: (
@@ -1635,6 +1642,7 @@ class TensorNameMap:
             "vision_model.model.layers.{bid}.self_attn.o_proj.linear", # gemma4
             "vision_tower.blocks.{bid}.attn.proj", # dots.ocr
             "vision_model.transformer.resblocks.{bid}.attn.out_proj", # Step3-VL
+            "model.vision_tower.layers.{bid}.attn.proj", # muse-glimmer
         ),
 
         MODEL_TENSOR.V_ENC_ATTN_SINKS: (
@@ -1663,6 +1671,7 @@ class TensorNameMap:
             "vision_tower.blocks.{bid}.norm2", # dots.ocr
             "vision_model.transformer.resblocks.{bid}.ln_2", # Step3-VL
             "model.qwen2_model.model.model.layers.{bid}.post_attention_layernorm", # Deepseek-OCR-2 qwen2
+            "model.vision_tower.layers.{bid}.norm2", # muse-glimmer
         ),
 
         MODEL_TENSOR.V_ENC_FFN_UP: (
@@ -1687,6 +1696,7 @@ class TensorNameMap:
             "vision_model.model.layers.{bid}.mlp.up_proj", # gemma4
             "vision_model.transformer.resblocks.{bid}.mlp.c_fc", # Step3-VL
             "model.qwen2_model.model.model.layers.{bid}.mlp.up_proj", # Deepseek-OCR-2 qwen2
+            "model.vision_tower.layers.{bid}.mlp.fc1", # muse-glimmer
         ),
 
         MODEL_TENSOR.V_ENC_FFN_GATE: (
@@ -1719,6 +1729,7 @@ class TensorNameMap:
             "model.qwen2_model.model.model.layers.{bid}.mlp.down_proj" , # Deepseek-OCR-2 qwen2
             "vision_model.model.layers.{bid}.mlp.down_proj", # gemma4
             "vision_model.transformer.resblocks.{bid}.mlp.c_proj", # Step3-VL
+            "model.vision_tower.layers.{bid}.mlp.fc2", # muse-glimmer
         ),
 
         MODEL_TENSOR.V_ENC_ATTN_POST_NORM: (
@@ -1753,6 +1764,7 @@ class TensorNameMap:
             "model.vision_model.pre_layrnorm", # Deepseek-OCR CLIP
             "vision_tower.patch_embed.patchifier.norm", # dots.ocr
             "vision_model.ln_pre", # Step3-VL
+            "model.vision_tower.ln_pre", # muse-glimmer
         ),
 
         MODEL_TENSOR.V_POST_NORM: (
@@ -1766,6 +1778,7 @@ class TensorNameMap:
             "visual.post_layernorm", # glm4v
             "siglip2.vision_model.post_layernorm",
             "model.qwen2_model.model.model.norm", # Deepseek-OCR-2 qwen2
+            "model.vision_tower.ln_post", # muse-glimmer
         ),
 
         MODEL_TENSOR.V_MM_POST_NORM: (

src/llama-arch.cpp

@@ -71,6 +71,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
     { LLM_ARCH_OLMO,             "olmo"             },
     { LLM_ARCH_OLMO2,            "olmo2"            },
     { LLM_ARCH_OLMOE,            "olmoe"            },
+    { LLM_ARCH_MUSE_GLIMMER,     "muse-glimmer"     },
     { LLM_ARCH_OPENELM,          "openelm"          },
     { LLM_ARCH_ARCTIC,           "arctic"           },
     { LLM_ARCH_DEEPSEEK,         "deepseek"         },

src/llama-arch.h

@@ -76,6 +76,7 @@ enum llm_arch {
     LLM_ARCH_OLMO,
     LLM_ARCH_OLMO2,
     LLM_ARCH_OLMOE,
+    LLM_ARCH_MUSE_GLIMMER,
     LLM_ARCH_OPENELM,
     LLM_ARCH_ARCTIC,
     LLM_ARCH_DEEPSEEK,

src/llama-model-saver.cpp

@@ -27,6 +27,7 @@ bool llama_model_saver_supports_arch(llm_arch arch) {
         case LLM_ARCH_APERTUS:
         case LLM_ARCH_MIMO2:
         case LLM_ARCH_STEP35:
+        case LLM_ARCH_MUSE_GLIMMER:
         case LLM_ARCH_MELLUM:
         case LLM_ARCH_LAGUNA:
             return false;

src/llama-model.cpp

@@ -128,6 +128,7 @@
 #include "models/mistral4.cpp"
 #include "models/modern-bert.cpp"
 #include "models/mpt.cpp"
+#include "models/muse-glimmer.cpp"
 #include "models/nanbeige.cpp"
 #include "models/nemotron-h-moe.cpp"
 #include "models/nemotron-h.cpp"
@@ -180,9 +181,12 @@
 #include "models/talkie.cpp"
 #include "models/wavtokenizer-dec.cpp"
 #include "models/xverse.cpp"
+#include "models/clip.cpp"
 
 static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params & params) {
     switch (arch) {
+        case LLM_ARCH_CLIP:
+            return new llama_model_clip(params);
         case LLM_ARCH_LLAMA:
             return new llama_model_llama(params);
         case LLM_ARCH_LLAMA4:
@@ -317,6 +321,8 @@ static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params
             return new llama_model_olmo2(params);
         case LLM_ARCH_OLMOE:
             return new llama_model_olmoe(params);
+        case LLM_ARCH_MUSE_GLIMMER:
+            return new llama_model_muse_glimmer(params);
         case LLM_ARCH_OPENELM:
             return new llama_model_openelm(params);
         case LLM_ARCH_GPTNEOX:
@@ -2374,6 +2380,9 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
                     params.ctx_type == LLAMA_CONTEXT_TYPE_MTP &&
                     (arch == LLM_ARCH_QWEN3NEXT || arch == LLM_ARCH_QWEN35 || arch == LLM_ARCH_QWEN35MOE);
 
+                const bool mtp_on_hybrid_nemotron =
+                    params.ctx_type == LLAMA_CONTEXT_TYPE_MTP && arch == LLM_ARCH_NEMOTRON_H_MOE;
+
                 if (llm_arch_is_recurrent(arch)) {
                     res = new llama_memory_recurrent(
                             *this,
@@ -2384,7 +2393,7 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
                             cparams.n_seq_max,
                             cparams.n_rs_seq,
                             nullptr);
-                } else if (llm_arch_is_hybrid(arch) && !mtp_on_hybrid_qwen) {
+                } else if (llm_arch_is_hybrid(arch) && !mtp_on_hybrid_qwen && !mtp_on_hybrid_nemotron) {
                     // The main difference between hybrid architectures is the
                     // layer filters, so pick the right one here
                     llama_memory_hybrid::layer_filter_cb filter_attn = nullptr;
@@ -2465,7 +2474,7 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
                         };
                     }
 
-                    if (mtp_on_hybrid_qwen) {
+                    if (mtp_on_hybrid_qwen || mtp_on_hybrid_nemotron) {
                         filter = [&](uint32_t il) { return il >= hparams.n_layer(); };
                     }
 
@@ -2737,6 +2746,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
         case LLM_ARCH_DEEPSEEK2OCR:
         case LLM_ARCH_DEEPSEEK32:
         case LLM_ARCH_DEEPSEEK4:
+        case LLM_ARCH_MUSE_GLIMMER:
         case LLM_ARCH_PLM:
         case LLM_ARCH_CHATGLM:
         case LLM_ARCH_GRANITE:

src/models/clip.cpp

@@ -0,0 +1,18 @@
+#include "models.h"
+
+// Stub to allow llama-quantize to open mmproj GGUFs
+
+[[noreturn]]
+void llama_model_clip::load_arch_hparams(llama_model_loader &) {
+    GGML_ABORT("CLIP is a quant-only stub; load_arch_hparams should not be called");
+}
+
+[[noreturn]]
+void llama_model_clip::load_arch_tensors(llama_model_loader &) {
+    GGML_ABORT("CLIP is a quant-only stub; load_arch_tensors should not be called");
+}
+
+[[noreturn]]
+std::unique_ptr<llm_graph_context> llama_model_clip::build_arch_graph(const llm_graph_params &) const {
+    GGML_ABORT("CLIP has no inference graph via llama_model dispatch; runtime lives in tools/mtmd/clip.cpp");
+}

src/models/models.h

@@ -386,6 +386,22 @@ struct llama_model_bloom : public llama_model_base {
 };
 
 
+// Quant-only stub for mmproj GGUFs
+// none of these are ever called, they only exist to satisfy the llama_model_base interface
+struct llama_model_clip : public llama_model_base {
+    llama_model_clip(const struct llama_model_params & params) : llama_model_base(params) {}
+
+    [[noreturn]]
+    void load_arch_hparams(llama_model_loader & ml) override;
+
+    [[noreturn]]
+    void load_arch_tensors(llama_model_loader & ml) override;
+
+    [[noreturn]]
+    std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
+};
+
+
 struct llama_model_mpt : public llama_model_base {
     llama_model_mpt(const struct llama_model_params & params) : llama_model_base(params) {}
     void load_arch_hparams(llama_model_loader & ml) override;
@@ -1028,6 +1044,19 @@ struct llama_model_olmoe : public llama_model_base {
 };
 
 
+struct llama_model_muse_glimmer : public llama_model_base {
+    llama_model_muse_glimmer(const struct llama_model_params & params) : llama_model_base(params) {}
+    void load_arch_hparams(llama_model_loader & ml) override;
+    void load_arch_tensors(llama_model_loader & ml) override;
+
+    struct graph : public llm_graph_context {
+        graph(const llama_model & model, const llm_graph_params & params);
+    };
+
+    std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
+};
+
+
 struct llama_model_openelm : public llama_model_base {
     llama_model_openelm(const struct llama_model_params & params) : llama_model_base(params) {}
     void load_arch_hparams(llama_model_loader & ml) override;
@@ -1461,6 +1490,10 @@ struct llama_model_nemotron_h_moe : public llama_model_nemotron_h {
 
     using graph = llama_model_nemotron_h::graph;
 
+    struct graph_mtp : public llm_graph_context {
+        graph_mtp(const llama_model & model, const llm_graph_params & params);
+    };
+
     std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
 };
 

src/models/muse-glimmer.cpp

@@ -0,0 +1,208 @@
+#include "models.h"
+
+void llama_model_muse_glimmer::load_arch_hparams(llama_model_loader & ml) {
+    ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
+    ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW,    hparams.n_swa);
+    ml.get_key(LLM_KV_FINAL_LOGIT_SOFTCAPPING,     hparams.f_final_logit_softcapping, false);
+    ml.get_key(LLM_KV_LOGIT_SCALE,                 hparams.f_logit_scale);
+
+    hparams.rope_freq_base_train_swa = hparams.rope_freq_base_train;
+    ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false);
+
+    hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;
+    uint32_t swa_period = 4;
+    if (ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, swa_period, false)) {
+        hparams.set_swa_pattern(swa_period);
+    } else {
+        ml.get_key_or_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl, hparams.n_layer());
+    }
+
+    switch (hparams.n_layer()) {
+        case 52: type = LLM_TYPE_30B; break;
+        default: type = LLM_TYPE_UNKNOWN;
+    }
+}
+
+void llama_model_muse_glimmer::load_arch_tensors(llama_model_loader &) {
+    LLAMA_LOAD_LOCALS;
+
+    tok_embd    = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD,  "weight"), {n_embd, n_vocab}, 0);
+    output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
+    output      = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab}, 0);
+
+    for (int i = 0; i < n_layer; ++i) {
+        auto & layer = layers[i];
+
+        // Pre/post-attention norms (Muse Glimmer's `weight + 1` applied at conversion time).
+        layer.attn_norm      = create_tensor(tn(LLM_TENSOR_ATTN_NORM,      "weight", i), {n_embd}, 0);
+        layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", i), {n_embd}, 0);
+
+        // Q/K/V/O projections.
+        create_tensor_qkv(layer, i, n_embd, n_embd_head_k * n_head, n_embd_k_gqa, n_embd_v_gqa, 0);
+        layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * n_head, n_embd}, 0);
+
+        // QK-norm. Weights are synthesized at conversion time to absorb `qk_scale_factor`.
+        layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {n_embd_head_k}, 0);
+        layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {n_embd_head_k}, 0);
+
+        // Attention output gate: sigmoid(gate) * attn_out before o_proj (same as afmoe).
+        layer.wqkv_gate = create_tensor(tn(LLM_TENSOR_ATTN_GATE, "weight", i), {n_embd, n_embd_head_k * n_head}, 0);
+
+        // Pre/post-FFN norms (FFN_PRE_NORM is aliased to LLM_TENSOR_FFN_NORM).
+        layer.ffn_norm      = create_tensor(tn(LLM_TENSOR_FFN_NORM,      "weight", i), {n_embd}, 0);
+        layer.ffn_post_norm = create_tensor(tn(LLM_TENSOR_FFN_POST_NORM, "weight", i), {n_embd}, 0);
+
+        // Dense FFN (unlike afmoe, no MoE branches).
+        layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, 0);
+        layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}, 0);
+        layer.ffn_up   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd, n_ff}, 0);
+    }
+}
+
+llama_model_muse_glimmer::graph::graph(const llama_model & model, const llm_graph_params & params)
+    : llm_graph_context(params) {
+    const int64_t n_embd_head = hparams.n_embd_head_v();
+    GGML_ASSERT(n_embd_head == hparams.n_embd_head_k());
+
+    // Different to f_norm_rms_eps for post-attn / post-FFN norms
+    const float post_norm_eps = 1e-8f;
+
+    ggml_tensor * cur;
+    ggml_tensor * inpL;
+
+    inpL = build_inp_embd(model.tok_embd);
+    inpL = build_norm(inpL, nullptr, nullptr, LLM_NORM_RMS, -1);
+    cb(inpL, "embd_norm", -1);
+
+    ggml_tensor * inp_pos = build_inp_pos();
+    auto * inp_attn = build_attn_inp_kv_iswa();
+    ggml_tensor * inp_out_ids = build_inp_out_ids();
+
+    const float kq_scale = 1.0f / sqrtf(float(n_embd_head));
+
+    for (int il = 0; il < n_layer; ++il) {
+        // expose per-layer residual for speculative drafts (see LLM_KV_TARGET_LAYERS).
+        res->t_layer_inp[il] = inpL;
+
+        const float freq_base_l  = model.get_rope_freq_base (cparams, il);
+        const float freq_scale_l = model.get_rope_freq_scale(cparams, il);
+
+        ggml_tensor * inpSA = inpL;
+
+        // RoPE runs on the SWA layers, NoPE on full ones.
+        const bool use_rope = hparams.is_swa(il);
+
+        // pre-attention norm (weight+1 folded at conversion time)
+        cur = build_norm(inpL, model.layers[il].attn_norm, NULL, LLM_NORM_RMS, il);
+        cb(cur, "attn_norm", il);
+
+        // self-attention: attention output gate around SDPA (afmoe.cpp:147-191)
+        {
+            ggml_tensor * attn_inp = cur;  // save input for gate computation
+
+            auto [Qcur, Kcur, Vcur] = build_qkv(model.layers[il], cur,
+                    n_embd_head, n_head, n_head_kv, il);
+
+            // gate = wqkv_gate @ attn_inp (from pre-attn hidden state)
+            ggml_tensor * gate = build_lora_mm(model.layers[il].wqkv_gate, attn_inp);
+            cb(gate, "attn_gate_proj", il);
+
+            // QK-norm. attn_q_norm weight was synthesized at conversion to broadcast
+            // qk_scale_factor across head_dim; attn_k_norm is identity (ones).
+            Qcur = build_norm(Qcur, model.layers[il].attn_q_norm, NULL, LLM_NORM_RMS, il);
+            Kcur = build_norm(Kcur, model.layers[il].attn_k_norm, NULL, LLM_NORM_RMS, il);
+            cb(Qcur, "Qcur_normed", il);
+            cb(Kcur, "Kcur_normed", il);
+
+            if (use_rope) {
+                Qcur = ggml_rope_ext(
+                        ctx0, Qcur, inp_pos, nullptr,
+                        n_rot, rope_type, n_ctx_orig, freq_base_l, freq_scale_l,
+                        ext_factor, attn_factor, beta_fast, beta_slow);
+                cb(Qcur, "Qcur_rope", il);
+
+                Kcur = ggml_rope_ext(
+                        ctx0, Kcur, inp_pos, nullptr,
+                        n_rot, rope_type, n_ctx_orig, freq_base_l, freq_scale_l,
+                        ext_factor, attn_factor, beta_fast, beta_slow);
+                cb(Kcur, "Kcur_rope", il);
+            }
+
+            // SDPA. wo is deferred; the gate goes between attn_out and o_proj.
+            cur = build_attn(inp_attn,
+                    NULL, NULL, NULL,
+                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);
+            cb(cur, "attn_out", il);
+
+            gate = ggml_sigmoid(ctx0, gate);
+            cb(gate, "attn_gate_sig", il);
+            cur = ggml_mul(ctx0, cur, gate);
+            cb(cur, "attn_gated", il);
+
+            cur = build_lora_mm(model.layers[il].wo, cur, model.layers[il].wo_s);
+            cb(cur, "attn_o_proj", il);
+        }
+
+        cur = ggml_rms_norm(ctx0, cur, post_norm_eps);
+        cur = ggml_mul(ctx0, cur, model.layers[il].attn_post_norm);
+        cb(cur, "attn_post_norm", il);
+
+        if (il == n_layer - 1 && inp_out_ids) {
+            cur   = ggml_get_rows(ctx0,   cur, inp_out_ids);
+            inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
+        }
+
+        ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
+        cb(ffn_inp, "ffn_inp", il);
+
+        // pre-FFN norm
+        cur = build_norm(ffn_inp, model.layers[il].ffn_norm, NULL, LLM_NORM_RMS, il);
+        cb(cur, "ffn_norm", il);
+
+        // SwiGLU dense FFN
+        cur = build_ffn(cur,
+                model.layers[il].ffn_up,   NULL, NULL,
+                model.layers[il].ffn_gate, NULL, NULL,
+                model.layers[il].ffn_down, NULL, NULL,
+                NULL,
+                LLM_FFN_SILU, LLM_FFN_PAR, il);
+        cb(cur, "ffn_out", il);
+
+        cur = ggml_rms_norm(ctx0, cur, post_norm_eps);
+        cur = ggml_mul(ctx0, cur, model.layers[il].ffn_post_norm);
+        cb(cur, "ffn_post_norm", il);
+
+        cur = ggml_add(ctx0, cur, ffn_inp);
+        cur = build_cvec(cur, il);
+        cb(cur, "l_out", il);
+
+        inpL = cur;
+    }
+
+    cur = inpL;
+
+    // final norm
+    cur = build_norm(cur, model.output_norm, NULL, LLM_NORM_RMS, -1);
+    cb(cur, "result_norm", -1);
+    res->t_embd = cur;
+
+    // lm_head, followed by output multiplier
+    cur = build_lora_mm(model.output, cur, model.output_s);
+    cur = ggml_scale(ctx0, cur, hparams.f_logit_scale);
+
+    // Final logit tanh softcap (from gemma3.cpp).
+    if (hparams.f_final_logit_softcapping) {
+        cur = ggml_scale(ctx0, cur, 1.0f / hparams.f_final_logit_softcapping);
+        cur = ggml_tanh(ctx0, cur);
+        cur = ggml_scale(ctx0, cur, hparams.f_final_logit_softcapping);
+    }
+
+    cb(cur, "result_output", -1);
+    res->t_logits = cur;
+
+    ggml_build_forward_expand(gf, cur);
+}
+
+std::unique_ptr<llm_graph_context> llama_model_muse_glimmer::build_arch_graph(const llm_graph_params & params) const {
+    return std::make_unique<graph>(*this, params);
+}

src/models/nemotron-h-moe.cpp

@@ -1,6 +1,156 @@
 #include "models.h"
 
 std::unique_ptr<llm_graph_context> llama_model_nemotron_h_moe::build_arch_graph(const llm_graph_params & params) const {
+    if (params.gtype == LLM_GRAPH_TYPE_DECODER_MTP) {
+        return std::make_unique<graph_mtp>(*this, params);
+    }
     return std::make_unique<graph>(*this, params);
 }
 
+// MTP draft head for Nemotron-H MoE
+llama_model_nemotron_h_moe::graph_mtp::graph_mtp(const llama_model & model, const llm_graph_params & params)
+    : llm_graph_context(params) {
+    GGML_ASSERT(hparams.n_layer_nextn == 1 && "NEMOTRON_H_MOE MTP currently supports a single MTP block");
+
+    const int64_t n_embd_head = hparams.n_embd_head_v();
+    GGML_ASSERT(n_embd_head == hparams.n_embd_head_k());
+
+    const int il = hparams.n_layer();
+    const auto & layer = model.layers[il];
+
+    GGML_ASSERT(layer.nextn.eh_proj && layer.nextn.enorm && layer.nextn.hnorm);
+    GGML_ASSERT(layer.ffn_gate_inp);
+
+    // token embedding weights
+    ggml_tensor * tok_embd_w = layer.nextn.embed_tokens ? layer.nextn.embed_tokens : model.tok_embd;
+    GGML_ASSERT(tok_embd_w != nullptr && "NEMOTRON_H_MOE MTP requires token embeddings");
+
+    auto inp = std::make_unique<llm_graph_input_embd_h>(hparams.n_embd);
+
+    inp->tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens);
+    ggml_set_input(inp->tokens);
+
+    inp->embd = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd_inp(), n_tokens);
+    ggml_set_input(inp->embd);
+
+    ggml_tensor * tok_embd;
+    if (ubatch.token) {
+        tok_embd = ggml_get_rows(ctx0, tok_embd_w, inp->tokens);
+    } else {
+        tok_embd = inp->embd;
+    }
+    cb(tok_embd, "mtp_tok_embd", il);
+
+    inp->h = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd, n_tokens);
+    ggml_set_input(inp->h);
+    ggml_set_name(inp->h, "mtp_h_input");
+
+    ggml_tensor * h_embd = inp->h;
+
+    res->add_input(std::move(inp));
+
+    ggml_tensor * inp_out_ids = build_inp_out_ids();
+
+    // attention fills KV over all tokens, but the MoE is position-wise: gather output rows before
+    // it to save FFN compute (unless unmasked embeddings_nextn needs the full-length hidden state)
+    const bool emit_h_nextn    = cparams.embeddings_nextn;
+    const bool crop_before_ffn = inp_out_ids && (!emit_h_nextn || cparams.embeddings_nextn_masked);
+
+    auto * inp_attn = build_attn_inp_kv();
+
+    ggml_tensor * h_norm = build_norm(h_embd, layer.nextn.hnorm, nullptr, LLM_NORM_RMS, il);
+    cb(h_norm, "mtp_hnorm", il);
+    ggml_tensor * e_norm = build_norm(tok_embd, layer.nextn.enorm, nullptr, LLM_NORM_RMS, il);
+    cb(e_norm, "mtp_enorm", il);
+
+    ggml_tensor * concat = ggml_concat(ctx0, e_norm, h_norm, /*dim=*/ 0);
+    cb(concat, "mtp_concat", il);
+
+    ggml_tensor * cur = build_lora_mm(layer.nextn.eh_proj, concat, layer.nextn.eh_proj_s);
+    cb(cur, "mtp_eh_proj", il);
+
+    // dense NoPE attention sub-layer (mtp.layers.0)
+    ggml_tensor * inpSA = cur;
+    cur = build_norm(cur, layer.attn_norm, nullptr, LLM_NORM_RMS, il);
+    cb(cur, "mtp_attn_norm", il);
+
+    {
+        auto [Qcur, Kcur, Vcur] = build_qkv(layer, cur, n_embd_head, hparams.n_head(il), hparams.n_head_kv(il), il);
+        const float kq_scale = hparams.f_attention_scale == 0.0f
+            ? 1.0f / sqrtf(float(n_embd_head)) : hparams.f_attention_scale;
+        cur = build_attn(inp_attn, layer.wo, layer.wo_b, layer.wo_s,
+                Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);
+        cb(cur, "mtp_attn_out", il);
+    }
+
+    cur = ggml_add(ctx0, cur, inpSA);
+    cb(cur, "mtp_attn_residual", il);
+
+    // gather the output rows here so the MoE FFN below only runs on the positions we keep
+    if (crop_before_ffn) {
+        cur = ggml_get_rows(ctx0, cur, inp_out_ids);
+    }
+
+    // MoE FFN sub-layer (mtp.layers.1)
+    ggml_tensor * ffn_residual = cur;
+    cur = build_norm(cur, layer.attn_post_norm, nullptr, LLM_NORM_RMS, il);
+    cb(cur, "mtp_attn_post_norm", il);
+
+    {
+        ggml_tensor * router_logits = build_lora_mm(layer.ffn_gate_inp, cur);
+        cb(router_logits, "mtp_ffn_moe_logits", il);
+
+        ggml_tensor * moe_out =
+            build_moe_ffn(cur,
+                layer.ffn_gate_inp,
+                layer.ffn_up_exps,
+                nullptr, // no gate
+                layer.ffn_down_exps,
+                layer.ffn_exp_probs_b,
+                n_expert, n_expert_used,
+                LLM_FFN_RELU_SQR, hparams.expert_weights_norm,
+                hparams.expert_weights_scale,
+                LLAMA_EXPERT_GATING_FUNC_TYPE_SIGMOID,
+                il,
+                router_logits, nullptr,
+                layer.ffn_up_exps_s,
+                nullptr, // no gate
+                layer.ffn_down_exps_s);
+        cb(moe_out, "mtp_ffn_moe_out", il);
+
+        ggml_tensor * ffn_shexp = build_ffn(cur,
+                layer.ffn_up_shexp,   NULL, layer.ffn_up_shexp_s,
+                NULL,                 NULL, NULL,
+                layer.ffn_down_shexp, NULL, layer.ffn_down_shexp_s,
+                NULL,
+                LLM_FFN_RELU_SQR, LLM_FFN_PAR, il);
+        cb(ffn_shexp, "mtp_ffn_shexp", il);
+
+        cur = ggml_add(ctx0, moe_out, ffn_shexp);
+        cb(cur, "mtp_ffn_out", il);
+    }
+
+    cur = ggml_add(ctx0, cur, ffn_residual);
+    cb(cur, "mtp_post_ffn", il);
+
+    // final head norm: the MTP head has its own LayerNorm
+    GGML_ASSERT(layer.nextn.shared_head_norm && "NEMOTRON_H_MOE MTP: missing final head norm");
+    cur = build_norm(cur, layer.nextn.shared_head_norm, nullptr, LLM_NORM, -1);
+
+    cb(cur, "h_nextn", -1);
+    res->t_h_nextn = cur;
+
+    if (!crop_before_ffn && inp_out_ids) {
+        cur = ggml_get_rows(ctx0, cur, inp_out_ids);
+    }
+
+    // LM head
+    ggml_tensor * head_w = layer.nextn.shared_head_head ? layer.nextn.shared_head_head : model.output;
+    ggml_tensor * head_s = layer.nextn.shared_head_head ? layer.nextn.shared_head_head_s : model.output_s;
+    GGML_ASSERT(head_w != nullptr && "NEMOTRON_H_MOE MTP requires an output projection");
+    cur = build_lora_mm(head_w, cur, head_s);
+    cb(cur, "result_output", -1);
+
+    res->t_logits = cur;
+    ggml_build_forward_expand(gf, cur);
+}

src/models/nemotron-h.cpp

@@ -7,13 +7,18 @@ void llama_model_nemotron_h::load_arch_hparams(llama_model_loader & ml) {
     ml.get_key(LLM_KV_SSM_TIME_STEP_RANK, hparams.ssm_dt_rank);
     ml.get_key(LLM_KV_SSM_GROUP_COUNT,    hparams.ssm_n_group);
 
+    // NextN/MTP: optional draft head appended as extra trailing block(s)
+    ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false);
+    GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer_all");
+
     // A layer is recurrent IFF the n_head_kv value is set to 0 and
-    // the n_ff value is set to 0
-    for (uint32_t i = 0; i < hparams.n_layer(); ++i) {
-        hparams.is_recr_impl[i] = (hparams.n_head_kv(i) == 0 && hparams.n_ff(i) == 0);
+    // the n_ff value is set to 0. Appended MTP blocks are dense (non-recurrent)
+    for (uint32_t i = 0; i < hparams.n_layer_all; ++i) {
+        hparams.is_recr_impl[i] = i < hparams.n_layer() && hparams.n_head_kv(i) == 0 && hparams.n_ff(i) == 0;
     }
 
     ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
+    ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS,     hparams.f_norm_eps); // MTP head final_layernorm
 
     ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH,        hparams.n_ff_exp,        false);
     ml.get_key(LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH, hparams.n_ff_shexp,      false);
@@ -30,9 +35,13 @@ void llama_model_nemotron_h::load_arch_hparams(llama_model_loader & ml) {
     }
 }
 
-void llama_model_nemotron_h::load_arch_tensors(llama_model_loader &) {
+void llama_model_nemotron_h::load_arch_tensors(llama_model_loader & ml) {
     LLAMA_LOAD_LOCALS;
 
+    const bool mtp_only    = hparams.n_layer_nextn > 0 && ml.get_weight("blk.0.attn_norm.weight") == nullptr;
+    const int  trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0;
+    const int  mtp_flags   = !ml.load_mtp ? TENSOR_SKIP : 0;
+
     // mamba2 Mixer SSM params
     // NOTE: int64_t for tensor dimensions
     const int64_t d_conv     = hparams.ssm_d_conv;
@@ -60,61 +69,94 @@ void llama_model_nemotron_h::load_arch_tensors(llama_model_loader &) {
         auto & layer = layers[i];
 
         // all blocks use the attn norm
-        layer.attn_norm  = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);
+        layer.attn_norm  = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, trunk_flags);
 
         if (hparams.is_recr(i)) {
             // ssm layers
-            layer.ssm_in = create_tensor(tn(LLM_TENSOR_SSM_IN, "weight", i), {n_embd, d_in_proj}, 0);
+            layer.ssm_in = create_tensor(tn(LLM_TENSOR_SSM_IN, "weight", i), {n_embd, d_in_proj}, trunk_flags);
 
-            layer.ssm_conv1d = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "weight", i), {d_conv, d_inner + 2*n_group*d_state}, 0);
+            layer.ssm_conv1d = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "weight", i), {d_conv, d_inner + 2*n_group*d_state}, trunk_flags);
             layer.ssm_conv1d_b = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "bias", i), {d_inner + 2*n_group*d_state}, TENSOR_NOT_REQUIRED);
 
-            layer.ssm_dt_b = create_tensor(tn(LLM_TENSOR_SSM_DT, "bias", i), {n_ssm_head}, 0);
+            layer.ssm_dt_b = create_tensor(tn(LLM_TENSOR_SSM_DT, "bias", i), {n_ssm_head}, trunk_flags);
 
             // no "weight" suffix for these
-            layer.ssm_a = create_tensor(tn(LLM_TENSOR_SSM_A, i), {1, n_ssm_head}, 0);
-            layer.ssm_d = create_tensor(tn(LLM_TENSOR_SSM_D, i), {1, n_ssm_head}, 0);
+            layer.ssm_a = create_tensor(tn(LLM_TENSOR_SSM_A, i), {1, n_ssm_head}, trunk_flags);
+            layer.ssm_d = create_tensor(tn(LLM_TENSOR_SSM_D, i), {1, n_ssm_head}, trunk_flags);
 
-            layer.ssm_norm = create_tensor(tn(LLM_TENSOR_SSM_NORM, "weight", i), {d_inner / n_group, n_group}, 0);
+            layer.ssm_norm = create_tensor(tn(LLM_TENSOR_SSM_NORM, "weight", i), {d_inner / n_group, n_group}, trunk_flags);
 
             // out_proj
-            layer.ssm_out = create_tensor(tn(LLM_TENSOR_SSM_OUT, "weight", i), {d_inner, n_embd}, 0);
+            layer.ssm_out = create_tensor(tn(LLM_TENSOR_SSM_OUT, "weight", i), {d_inner, n_embd}, trunk_flags);
         } else if (hparams.n_ff(i) == 0) {
             // attention layers (with optional bias)
             const int64_t n_head_i = hparams.n_head(i);
             const int64_t n_embd_k_gqa_i = hparams.n_embd_k_gqa(i);
             const int64_t n_embd_v_gqa_i = hparams.n_embd_v_gqa(i);
-            create_tensor_qkv(layer, i, n_embd, n_embd_head_k * n_head_i, n_embd_k_gqa_i, n_embd_v_gqa_i, 0);
-            layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * n_head_i, n_embd}, 0);
+            create_tensor_qkv(layer, i, n_embd, n_embd_head_k * n_head_i, n_embd_k_gqa_i, n_embd_v_gqa_i, trunk_flags);
+            layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * n_head_i, n_embd}, trunk_flags);
             layer.wo_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}, TENSOR_NOT_REQUIRED);
         }  else {
             if (n_expert != 0) {
                 const int64_t n_ff_exp = hparams.n_ff_exp ? hparams.n_ff_exp : n_ff / n_expert_used;
                 const int64_t n_ff_shexp = hparams.n_ff_shexp;
 
-                layer.ffn_gate_inp    = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP,  "weight", i), { n_embd, n_expert}, 0);
-                layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert         }, 0);
+                layer.ffn_gate_inp    = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP,  "weight", i), { n_embd, n_expert}, trunk_flags);
+                layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert         }, trunk_flags);
 
                 // MoE branch
                 layer.ffn_latent_down = create_tensor(tn(LLM_TENSOR_FFN_LATENT_DOWN, "weight", i), {n_embd, moe_n_embd}, TENSOR_NOT_REQUIRED);
                 layer.ffn_latent_up   = create_tensor(tn(LLM_TENSOR_FFN_LATENT_UP,   "weight", i), {moe_n_embd, n_embd}, TENSOR_NOT_REQUIRED);
 
-                layer.ffn_down_exps   = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp,   moe_n_embd, n_expert}, 0);
-                layer.ffn_up_exps     = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS,   "weight", i), {moe_n_embd, n_ff_exp, n_expert}, 0);
+                layer.ffn_down_exps   = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp,   moe_n_embd, n_expert}, trunk_flags);
+                layer.ffn_up_exps     = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS,   "weight", i), {moe_n_embd, n_ff_exp, n_expert}, trunk_flags);
 
                 // Shared expert branch
-                layer.ffn_down_shexp  = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), {n_ff_shexp, n_embd}, 0);
-                layer.ffn_up_shexp    = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP,   "weight", i), {n_embd, n_ff_shexp}, 0);
+                layer.ffn_down_shexp  = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), {n_ff_shexp, n_embd}, trunk_flags);
+                layer.ffn_up_shexp    = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP,   "weight", i), {n_embd, n_ff_shexp}, trunk_flags);
 
             } else {
                 // mlp layers
-                layer.ffn_down   = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  hparams.n_ff(i), n_embd}, 0);
-                layer.ffn_up     = create_tensor(tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   hparams.n_ff(i)}, 0);
+                layer.ffn_down   = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {  hparams.n_ff(i), n_embd}, trunk_flags);
+                layer.ffn_up     = create_tensor(tn(LLM_TENSOR_FFN_UP,   "weight", i), {n_embd,   hparams.n_ff(i)}, trunk_flags);
                 layer.ffn_down_b = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "bias",   i), {n_embd}, TENSOR_NOT_REQUIRED);
                 layer.ffn_up_b   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "bias",   i), {hparams.n_ff(i)}, TENSOR_NOT_REQUIRED);
             }
         }
     }
+
+    // NextN/MTP draft head: each predict layer folds an attention sub-layer and a MoE
+    // sub-layer into a single trailing block
+    for (int i = n_layer; i < n_layer_all; ++i) {
+        auto & layer = layers[i];
+
+        const int64_t n_head_i       = hparams.n_head(i);
+        const int64_t n_embd_k_gqa_i = hparams.n_embd_k_gqa(i);
+        const int64_t n_embd_v_gqa_i = hparams.n_embd_v_gqa(i);
+        const int64_t n_ff_exp       = hparams.n_ff_exp ? hparams.n_ff_exp : n_ff / n_expert_used;
+        const int64_t n_ff_shexp     = hparams.n_ff_shexp;
+
+        // NextN input-fusion tensors
+        layer.nextn.enorm            = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM,            "weight", i), {n_embd}, mtp_flags);
+        layer.nextn.hnorm            = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM,            "weight", i), {n_embd}, mtp_flags);
+        layer.nextn.eh_proj          = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ,          "weight", i), {2*n_embd, n_embd}, mtp_flags);
+        layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", i), {n_embd}, mtp_flags);
+
+        // attention sub-layer
+        layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, mtp_flags);
+        create_tensor_qkv(layer, i, n_embd, n_embd_head_k * n_head_i, n_embd_k_gqa_i, n_embd_v_gqa_i, mtp_flags);
+        layer.wo   = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd_head_k * n_head_i, n_embd}, mtp_flags);
+        layer.wo_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias",   i), {n_embd}, mtp_flags | TENSOR_NOT_REQUIRED);
+
+        // MoE sub-layer
+        layer.attn_post_norm  = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM,  "weight", i), {n_embd}, mtp_flags);
+        layer.ffn_gate_inp    = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP,    "weight", i), {n_embd, n_expert}, mtp_flags);
+        layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias",   i), {n_expert}, mtp_flags);
+        layer.ffn_down_exps   = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS,   "weight", i), {n_ff_exp,   moe_n_embd, n_expert}, mtp_flags);
+        layer.ffn_up_exps     = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS,     "weight", i), {moe_n_embd, n_ff_exp,   n_expert}, mtp_flags);
+        layer.ffn_down_shexp  = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP,  "weight", i), {n_ff_shexp, n_embd}, mtp_flags);
+        layer.ffn_up_shexp    = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP,    "weight", i), {n_embd, n_ff_shexp}, mtp_flags);
+    }
 }
 
 std::unique_ptr<llm_graph_context> llama_model_nemotron_h::build_arch_graph(const llm_graph_params & params) const {
@@ -153,7 +195,7 @@ llama_model_nemotron_h::graph::graph(const llama_model & model, const llm_graph_
             cur = build_ffn_layer(cur, model, il);
         }
 
-        if (il == n_layer - 1 && inp_out_ids) {
+        if (il == n_layer - 1 && inp_out_ids && cparams.embeddings_nextn_masked) {
             cur   = ggml_get_rows(ctx0, cur, inp_out_ids);
             inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);
         }
@@ -170,6 +212,14 @@ llama_model_nemotron_h::graph::graph(const llama_model & model, const llm_graph_
 
     cur = build_norm(cur, model.output_norm, NULL, LLM_NORM_RMS, -1);
 
+    // seed for the MTP/NextN draft head
+    cb(cur, "h_nextn", -1);
+    res->t_h_nextn = cur;
+
+    if (!cparams.embeddings_nextn_masked && inp_out_ids) {
+        cur = ggml_get_rows(ctx0, cur, inp_out_ids);
+    }
+
     cb(cur, "result_norm", -1);
     res->t_embd = cur;
 

tools/mtmd/clip-impl.h

@@ -455,6 +455,7 @@ enum projector_type {
     PROJECTOR_TYPE_MIMO_AUDIO,
     PROJECTOR_TYPE_QWEN3TTS_SPKENC,
     PROJECTOR_TYPE_QWEN3TTS_GEN,
+    PROJECTOR_TYPE_MUSE_GLIMMER,
     PROJECTOR_TYPE_UNKNOWN,
 };
 
@@ -514,6 +515,7 @@ static std::map<projector_type, std::string> PROJECTOR_TYPE_NAMES = {
     { PROJECTOR_TYPE_PARAKEET,          "parakeet"},
     { PROJECTOR_TYPE_QWEN3TTS_SPKENC,   "qwen3tts_spkenc"},
     { PROJECTOR_TYPE_QWEN3TTS_GEN,      "qwen3tts_gen"},
+    { PROJECTOR_TYPE_MUSE_GLIMMER,      "muse-glimmer"},
 };
 
 static projector_type clip_projector_type_from_string(const std::string & str) {

tools/mtmd/clip-model.h

@@ -109,6 +109,11 @@ struct clip_hparams {
     int32_t downsample_query_side;
     int32_t downsample_window_side;
 
+    // Muse Glimmer vision (per-block sparse-window pattern, learned pos-emb, patch-temporal)
+    // NOTE: these perhaps shouldn't have the architecture prefix
+    int32_t muse_glimmer_patch_temporal = 0;
+    int32_t muse_glimmer_sparse_factor  = 0;
+
     // audio
     int32_t n_mel_bins = 0; // whisper preprocessor
     int32_t proj_stack_factor = 0; // ultravox

tools/mtmd/clip.cpp

@@ -69,6 +69,7 @@
 #include "models/qwen3a.cpp"
 #include "models/mimovl.cpp"
 #include "models/mimo-audio.cpp"
+#include "models/muse-glimmer.cpp"
 #include "models/qwen3tts-spkenc.cpp"
 #include "models/qwen3tts-gen.cpp"
 #include "models/step3vl.cpp"
@@ -1007,6 +1008,10 @@ static std::unique_ptr<clip_graph> clip_get_graph_builder(clip_ctx * ctx, const
             {
                 builder = std::make_unique<clip_graph_minimax_m3>(ctx, img);
             } break;
+        case PROJECTOR_TYPE_MUSE_GLIMMER:
+            {
+                builder = std::make_unique<clip_graph_muse_glimmer>(ctx, img);
+            } break;
         case PROJECTOR_TYPE_STEP3VL:
             {
                 builder = std::make_unique<clip_graph_step3vl>(ctx, img);
@@ -1653,6 +1658,17 @@ struct clip_model_loader {
                         hparams.set_limit_image_tokens(8, 576);
                         hparams.set_warmup_n_tokens(16*16);
                     } break;
+                case PROJECTOR_TYPE_MUSE_GLIMMER:
+                    {
+                        hparams.n_merge = 2; // pixel-shuffle downsample after the ViT
+                        hparams.image_resize_algo = RESIZE_ALGO_LANCZOS;
+                        hparams.rope_theta = 10000.0f;
+                        hparams.muse_glimmer_patch_temporal = 2;
+                        hparams.muse_glimmer_sparse_factor  = 4; // 3 sparse layers + 1 global, repeating
+                        get_u32(KEY_SPATIAL_MERGE_SIZE,  hparams.n_merge,             false);
+                        hparams.set_limit_image_tokens(1, 4096);
+                        hparams.set_warmup_n_tokens(32*32);
+                    } break;
                 case PROJECTOR_TYPE_MIMOVL:
                     {
                         hparams.n_merge = 2; // spatial_merge_size
@@ -2403,6 +2419,13 @@ struct clip_model_loader {
                     model.mm_merger_fc2_w = get_tensor(string_format(TN_MM_MERGER_FC2, "weight"));
                     model.mm_merger_fc2_b = get_tensor(string_format(TN_MM_MERGER_FC2, "bias"));
                 } break;
+            case PROJECTOR_TYPE_MUSE_GLIMMER:
+                {
+                    // 3-linear MLP: fc -> erf-GELU -> proj -> erf-GELU -> vision_proj (into LLM residual dim)
+                    model.mm_0_w = get_tensor(string_format(TN_LLAVA_PROJ, 0, "weight"));
+                    model.mm_1_w = get_tensor(string_format(TN_LLAVA_PROJ, 1, "weight"));
+                    model.mm_2_w = get_tensor(string_format(TN_LLAVA_PROJ, 2, "weight"));
+                } break;
             case PROJECTOR_TYPE_STEP3VL:
                 {
                     model.mm_0_w     = get_tensor(string_format(TN_LLAVA_PROJ, 0, "weight"));
@@ -3831,6 +3854,7 @@ int clip_n_output_tokens_x(const clip_ctx * ctx, const clip_image_f32 * img) {
         case PROJECTOR_TYPE_PADDLEOCR:
         case PROJECTOR_TYPE_HUNYUANVL:
         case PROJECTOR_TYPE_YOUTUVL:
+        case PROJECTOR_TYPE_MUSE_GLIMMER:
             return (img->nx() / params.patch_size) / 2;
         case PROJECTOR_TYPE_STEP3VL:
             return img->nx() / (params.patch_size * params.n_merge);
@@ -3856,6 +3880,7 @@ int clip_n_output_tokens_y(const clip_ctx * ctx, const clip_image_f32 * img) {
         case PROJECTOR_TYPE_PADDLEOCR:
         case PROJECTOR_TYPE_HUNYUANVL:
         case PROJECTOR_TYPE_YOUTUVL:
+        case PROJECTOR_TYPE_MUSE_GLIMMER:
             return (img->ny() / params.patch_size) / 2;
         case PROJECTOR_TYPE_STEP3VL:
             return img->ny() / (params.patch_size * params.n_merge);
@@ -3934,6 +3959,7 @@ int clip_n_output_tokens(const clip_ctx * ctx, const clip_image_f32 * img) {
         case PROJECTOR_TYPE_MINIMAX_M3:
         case PROJECTOR_TYPE_GLM4V:
         case PROJECTOR_TYPE_YOUTUVL:
+        case PROJECTOR_TYPE_MUSE_GLIMMER:
             {
                 // dynamic size (2 conv, so double patch size)
                 int x_patch = img->nx() / (params.patch_size * 2);
@@ -4279,6 +4305,70 @@ bool clip_encode(struct clip_ctx * ctx, struct clip_encode_params * params) {
 
     // set input per projector
     switch (ctx->model.proj_type) {
+        case PROJECTOR_TYPE_MUSE_GLIMMER:
+            {
+                const int grid_w = pos_w;            // image_size_width  / patch_size
+                const int grid_h = pos_h;            // image_size_height / patch_size
+                const int n_tok  = grid_w * grid_h;
+                const int pgrid  = (int) std::sqrt((double) ctx->model.position_embeddings->ne[1]); // 32
+                const int f      = hparams.n_merge;  // downsample 2
+
+                // pixel patchify runs inside the graph via build_inp() (ggml_conv_2d);
+                // pos-emb bilinear interp via resize_position_embeddings().
+
+                // --- sparse window grouping (pgrid x pgrid windows) ---
+                const int win = pgrid;
+                const int nwin_h = (grid_h + win - 1) / win;
+                const int nwin_w = (grid_w + win - 1) / win;
+                std::vector<int32_t> sp_perm; sp_perm.reserve(n_tok);
+                std::vector<int>     sp_slens;
+                for (int wy = 0; wy < nwin_h; wy++) {
+                    for (int wx = 0; wx < nwin_w; wx++) {
+                        int cnt = 0;
+                        for (int hh = 0; hh < win; hh++) {
+                            for (int ww = 0; ww < win; ww++) {
+                                const int gy = wy * win + hh;
+                                const int gx = wx * win + ww;
+                                if (gy < grid_h && gx < grid_w) { sp_perm.push_back(gy * grid_w + gx); cnt++; }
+                            }
+                        }
+                        if (cnt > 0) sp_slens.push_back(cnt);
+                    }
+                }
+                std::vector<int32_t> rpos_w(n_tok), rpos_h(n_tok), inv_perm(n_tok);
+                for (int i = 0; i < n_tok; i++) {
+                    const int orig = sp_perm[i];
+                    rpos_w[i] = (orig % grid_w) + 1; // 1-indexed
+                    rpos_h[i] = (orig / grid_w) + 1;
+                    inv_perm[orig] = i;
+                }
+                set_input_i32("muse_glimmer_sp_perm",  sp_perm);
+                set_input_i32("muse_glimmer_inv_perm", inv_perm);
+                set_input_i32("muse_glimmer_pos_w",    rpos_w);
+                set_input_i32("muse_glimmer_pos_h",    rpos_h);
+
+                // block-diagonal window mask (permuted order)
+                std::vector<float> sp_mask((size_t) n_tok * n_tok, -INFINITY);
+                {
+                    int off = 0;
+                    for (int s : sp_slens) {
+                        for (int a = 0; a < s; a++)
+                            for (int b = 0; b < s; b++)
+                                sp_mask[(size_t) (off + a) * n_tok + (off + b)] = 0.0f;
+                        off += s;
+                    }
+                }
+                set_input_f32("muse_glimmer_sp_mask", sp_mask);
+
+                // pixel-shuffle gather (original order): f*f spatial neighbours grouped
+                std::vector<int32_t> dsp; dsp.reserve(n_tok);
+                for (int oy = 0; oy < grid_h / f; oy++)
+                    for (int ox = 0; ox < grid_w / f; ox++)
+                        for (int ry = 0; ry < f; ry++)
+                            for (int rx = 0; rx < f; rx++)
+                                dsp.push_back((oy * f + ry) * grid_w + (ox * f + rx));
+                set_input_i32("muse_glimmer_ds_perm", dsp);
+            } break;
         case PROJECTOR_TYPE_MINICPMV:
             {
                 // inspired from siglip:
@@ -5455,6 +5545,8 @@ int clip_n_mmproj_embd(const struct clip_ctx * ctx) {
             return ctx->model.mm_model_mlp_3_w->ne[1];
         case PROJECTOR_TYPE_MINIMAX_M3:
             return ctx->model.mm_merger_fc2_b->ne[0];
+        case PROJECTOR_TYPE_MUSE_GLIMMER:
+            return ctx->model.mm_2_w->ne[1];
         case PROJECTOR_TYPE_QWEN2VL:
         case PROJECTOR_TYPE_QWEN25VL:
         case PROJECTOR_TYPE_EXAONE4_5:

tools/mtmd/models/models.h

@@ -365,3 +365,8 @@ private:
     ggml_tensor * build_newline_row(ggml_context * ctx0);
     ggml_tensor * append_rowwise_newlines(ggml_context * ctx0, ggml_tensor * tile_output);
 };
+
+struct clip_graph_muse_glimmer : clip_graph {
+    clip_graph_muse_glimmer(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {}
+    ggml_cgraph * build() override;
+};

tools/mtmd/models/muse-glimmer.cpp

@@ -0,0 +1,88 @@
+#include "models.h"
+
+// MuseGlimmer vision encoder: 50-layer ViT with 2D RoPE, sparse block-diagonal
+// window attention (every 4th + last layer global), pixel-shuffle downsample, then
+// adapter MLP + LLM's vision_projection.
+//
+// Several quantities are precomputed on host and fed as named graph inputs (filled in
+// clip.cpp set_input, PROJECTOR_TYPE_MUSE_GLIMMER branch):
+//   muse_glimmer_pos_w/_h [n_tok] i32         : 1-indexed RoPE positions (sparse-permuted order)
+//   muse_glimmer_sp_perm  [n_tok] i32         : window grouping permutation (applied after ln_pre)
+//   muse_glimmer_inv_perm [n_tok] i32         : inverse of sp_perm (applied after blocks)
+//   muse_glimmer_ds_perm  [n_tok] i32         : pixel-shuffle gather (original order)
+//   muse_glimmer_sp_mask  [n_tok, n_tok] f32  : block-diagonal window mask (sparse layers)
+ggml_cgraph * clip_graph_muse_glimmer::build() {
+    const int ds = hparams.n_merge;              // downsample factor (2)
+    const int sf = hparams.muse_glimmer_sparse_factor;   // 4
+    const int n_tok     = n_patches;
+    const int n_out     = (n_patches_x / ds) * (n_patches_y / ds);
+    const float rope_base = hparams.rope_theta;  // 10000
+
+    auto inp_i32 = [&](const char * name, int64_t n) {
+        ggml_tensor * t = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n);
+        ggml_set_name(t, name);
+        ggml_set_input(t);
+        return t;
+    };
+
+    ggml_tensor * pos_w    = inp_i32("muse_glimmer_pos_w",    n_tok);
+    ggml_tensor * pos_h    = inp_i32("muse_glimmer_pos_h",    n_tok);
+    ggml_tensor * sp_perm  = inp_i32("muse_glimmer_sp_perm",  n_tok);
+    ggml_tensor * inv_perm = inp_i32("muse_glimmer_inv_perm", n_tok);
+    ggml_tensor * ds_perm  = inp_i32("muse_glimmer_ds_perm",  n_tok);
+
+    ggml_tensor * sp_mask = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_tok, n_tok);
+    ggml_set_name(sp_mask, "muse_glimmer_sp_mask");
+    ggml_set_input(sp_mask);
+
+    // patchify via build_inp (conv2d over raw pixels) + bilinear-resized learned pos-emb
+    ggml_tensor * x = build_inp();                                                     // [n_embd, n_tok, 1]
+    x = ggml_add(ctx0, x, resize_position_embeddings(GGML_SCALE_MODE_BILINEAR));
+    cb(x, "after_posemb", -1);
+
+    // group patches into pgrid x pgrid windows (sparse attention order)
+    x = ggml_get_rows(ctx0, x, sp_perm);
+    cb(x, "after_sp_perm", -1);
+
+    // per-layer mask: sparse layers get sp_mask, global layers (every sf-th and last) get none
+    std::vector<ggml_tensor *> attn_mask_layers(n_layer);
+    for (int il = 0; il < n_layer; ++il) {
+        const bool is_global = (il == n_layer - 1) || ((il + 1) % sf == 0);
+        attn_mask_layers[il] = is_global ? nullptr : sp_mask;
+    }
+
+    // 2D RoPE: first half of head_dim uses width pos, second half uses height pos
+    auto add_pos = [&](ggml_tensor * cur, const clip_layer &) {
+        return build_rope_2d(ctx0, cur, pos_w, pos_h, rope_base, false);
+    };
+
+    build_vit_opts opts;
+    opts.attn_mask_layers = std::move(attn_mask_layers);
+
+    // pre_ln, per-layer transformer, post_ln (all inside build_vit); reference uses exact (erf) GELU
+    x = build_vit(x, n_tok, NORM_TYPE_NORMAL, FFN_GELU_ERF, nullptr, add_pos, opts);
+
+    // un-permute back to original grid order
+    x = ggml_get_rows(ctx0, x, inv_perm);
+    cb(x, "after_inv_perm", -1);
+
+    // pixel-shuffle downsample: gather f*f spatial neighbors then concat channel-outer.
+    // out[c*(ds*ds)+s, o] = x[ds_perm gathered][o*(ds*ds)+s, c]
+    x = ggml_get_rows(ctx0, x, ds_perm);                 // [n_embd, n_tok], grouped
+    x = ggml_reshape_3d(ctx0, x, n_embd, ds * ds, n_out);// [c, s, o]
+    x = ggml_permute(ctx0, x, 1, 0, 2, 3);               // [s, c, o]
+    x = ggml_cont(ctx0, x);
+    x = ggml_reshape_2d(ctx0, x, n_embd * ds * ds, n_out); // [6144, n_out]
+    cb(x, "encoder_out", -1);
+
+    // adapter (6144->4096->4096, exact GELU each) + LLM vision_projection (4096->6656)
+    x = build_mm(model.mm_0_w, x);
+    x = ggml_gelu_erf(ctx0, x);
+    x = build_mm(model.mm_1_w, x);
+    x = ggml_gelu_erf(ctx0, x);
+    x = build_mm(model.mm_2_w, x);                       // [6656, n_out]
+    cb(x, "projected", -1);
+
+    ggml_build_forward_expand(gf, x);
+    return gf;
+}

tools/mtmd/mtmd-image.cpp

@@ -1615,3 +1615,65 @@ mtmd_image_preproc_out mtmd_image_preprocessor_granite::preprocess(const clip_im
     }
     return output;
 }
+
+//
+// mtmd_image_preprocessor_muse_glimmer
+//
+
+// Replicates transformers' get_aspect_ratio_preserving_size
+static clip_image_size muse_glimmer_grid_size(int img_w, int img_h, int patch_hw, int max_tokens) {
+    double i_nph = (double) img_h / patch_hw;
+    double i_npw = (double) img_w / patch_hw;
+    const double ratio = i_nph > 0.0 ? i_npw / i_nph : 1.0;
+    if (i_nph * i_npw > (double) max_tokens) {
+        i_nph = std::sqrt((double) max_tokens / ratio);
+        i_npw = i_nph * ratio;
+    }
+    const int hs[2] = { (int) std::floor(i_nph), (int) std::ceil(i_nph) };
+    const int ws[2] = { (int) std::floor(i_npw), (int) std::ceil(i_npw) };
+    const double target_ar = (double) img_h / (double) img_w;
+    int    best_nph = -1;
+    int    best_npw = -1;
+    double best_d   = 0.0;
+    for (int a = 0; a < 2; ++a) {
+        for (int b = 0; b < 2; ++b) {
+            const int nph = hs[a];
+            const int npw = ws[b];
+            if (nph < 1 || npw < 1 || nph * npw > max_tokens) {
+                continue;
+            }
+            const double d = std::fabs((double) nph / (double) npw - target_ar);
+            const int n_tokens      = nph * npw;
+            const int best_n_tokens = best_nph * best_npw;
+            if (best_nph < 0 || d < best_d || (d == best_d && n_tokens > best_n_tokens)) {
+                best_nph = nph;
+                best_npw = npw;
+                best_d   = d;
+            }
+        }
+    }
+    if (best_nph < 0) { // no candidate fit under the cap: round and clamp
+        best_nph = std::max(1, (int) std::lround(i_nph));
+        best_npw = std::max(1, (int) std::lround(i_npw));
+    }
+    return clip_image_size{ best_npw * patch_hw, best_nph * patch_hw };
+}
+
+mtmd_image_preproc_out mtmd_image_preprocessor_muse_glimmer::preprocess(const clip_image_u8 & img) {
+    const int patch_hw   = hparams.patch_size * hparams.n_merge;
+    const int patch_area = hparams.patch_size * hparams.patch_size * hparams.n_merge * hparams.n_merge;
+    GGML_ASSERT(patch_area > 0 && hparams.image_max_pixels > 0);
+    const int max_tokens = hparams.image_max_pixels / patch_area;
+
+    const clip_image_size original_size = img.get_size();
+    const clip_image_size target_size   = muse_glimmer_grid_size(
+        original_size.width, original_size.height, patch_hw, max_tokens);
+
+    // PIL resizes directly to (target_w, target_h) -- a stretch, no padding.
+    clip_image_u8 resized_image;
+    img_tool::resize(img, resized_image, target_size, hparams.image_resize_algo, PAD_NONE);
+
+    mtmd_image_preproc_out output;
+    output.append(hparams, resized_image, true);
+    return output;
+}

tools/mtmd/mtmd-image.h

@@ -230,3 +230,9 @@ struct mtmd_image_preprocessor_granite : mtmd_image_preprocessor_llava_uhd {
     mtmd_image_preprocessor_granite(const clip_ctx * ctx) : mtmd_image_preprocessor_llava_uhd(ctx) {}
     mtmd_image_preproc_out preprocess(const clip_image_u8 & img) override;
 };
+
+// pick the patch grid closest to the input aspect ratio under the per-image token cap, stretch-resize.
+struct mtmd_image_preprocessor_muse_glimmer : mtmd_image_preprocessor {
+    mtmd_image_preprocessor_muse_glimmer(const clip_ctx * ctx) : mtmd_image_preprocessor(ctx) {}
+    mtmd_image_preproc_out preprocess(const clip_image_u8 & img) override;
+};

tools/mtmd/mtmd.cpp

@@ -699,6 +699,12 @@ struct mtmd_context {
                     img_end = "]<]end of image[>[";
                     image_preproc = std::make_unique<mtmd_image_preprocessor_dyn_size>(ctx_v);
                 } break;
+            case PROJECTOR_TYPE_MUSE_GLIMMER:
+                {
+                    img_beg = "<|image_start|>";
+                    img_end = "<|image_end|>";
+                    image_preproc = std::make_unique<mtmd_image_preprocessor_muse_glimmer>(ctx_v);
+                } break;
             case PROJECTOR_TYPE_YOUTUVL:
                 {
                     // <|vision_start|> ... (image embeddings) ... <|vision_end|>

tools/server/README-dev.md

@@ -201,7 +201,7 @@ Invoke a tool call, request body is a JSON object with:
 
 Headers:
 - `x-tool-cwd`: optional; if set, use as the CWD for tool; this is not part of tool's params because it's meant to be set by the runtime, not the LLM itself
-- `x-tool-runtime`: optional; if set, run the tool inside this isolate instead of on the host. Only `docker-container:<id>` is supported for now, using an already-running container
+- `x-tool-runtime`: optional; if set, run the tool inside this isolate instead of on the host. Either `docker-container:<id>` or `podman-container:<id>`, using an already-running container, or `ssh:<target>`, running the tool on a remote host
 
 Returns JSON object. There are two response formats (MCP tools use the same two formats: their result content is concatenated into `plain_text_response`, and RPC or tool errors are surfaced as the `error` string):
 

tools/server/server-tools.cpp

@@ -10,6 +10,7 @@
 #include <ctime>
 #include <atomic>
 #include <cstring>
+#include <cctype>
 #include <cstdint>
 #include <cstdlib>
 #include <algorithm>
@@ -25,6 +26,11 @@
 #       define NOMINMAX
 #   endif
 #   include <windows.h>
+#   include <fcntl.h>
+#   include <io.h>
+#else
+#   include <cerrno>
+#   include <unistd.h>
 #endif
 
 namespace fs = std::filesystem;
@@ -176,7 +182,7 @@ public:
             const std::function<bool(const std::string &)> & on_chunk = nullptr) const = 0;
 };
 
-// shared subprocess execution helper, used by both the local and the docker-backed tools_io implementations.
+// shared subprocess execution helper, used by both the local and the isolate-backed tools_io implementations.
 // combine_stderr=false when the raw stdout bytes must not be tainted by stderr, e.g. reading file contents.
 static tools_io::exec_result run_subprocess(
         const std::vector<std::string> & args,
@@ -184,7 +190,8 @@ static tools_io::exec_result run_subprocess(
         int timeout_secs,
         const std::function<bool(const std::string &)> & on_chunk,
         bool combine_stderr,
-        const std::string & cwd = "") {
+        const std::string & cwd = "",
+        const std::string * stdin_data = nullptr) {
     tools_io::exec_result res;
 
     common_subproc proc;
@@ -216,26 +223,59 @@ static tools_io::exec_result run_subprocess(
         }
     });
 
+    // write stdin before reading stdout, the child drains stdin as it goes
+    // always close stdin, a transport client waits forever if its stdin pipe stays open
+    if (FILE * in = proc.stdin_file()) {
+        if (stdin_data != nullptr && !stdin_data->empty()) {
+#if defined(_WIN32)
+            // pipe fds default to CRT text mode: binary keeps the bytes untranslated
+            _setmode(_fileno(in), _O_BINARY);
+#endif
+            // a short write is not an error by itself, the exit code below decides
+            fwrite(stdin_data->data(), 1, stdin_data->size(), in);
+        }
+        fflush(in);
+    }
+    proc.close_stdin();
+
     FILE * f = proc.stdout_file();
     std::string output;
     bool truncated = false;
     if (f) {
+#if defined(_WIN32)
+        // pipe fds default to CRT text mode: binary keeps the bytes untranslated
+        _setmode(_fileno(f), _O_BINARY);
+#endif
+        // read raw bytes, not lines: the output can hold NUL and must arrive as soon as it is ready
+        // keep draining past the size cap, else the child blocks on a full pipe
         char buf[4096];
-        while (fgets(buf, sizeof(buf), f) != nullptr) {
-            if (!truncated) {
-                size_t len = strlen(buf);
-                if (output.size() + len <= max_output) {
-                    output.append(buf, len);
-                    if (on_chunk && !on_chunk(console_output_to_utf8(std::string(buf, len)))) {
-                        proc.terminate();
-                        break;
-                    }
-                } else {
-                    size_t remaining = max_output - output.size();
-                    output.append(buf, remaining);
-                    if (on_chunk && remaining > 0) on_chunk(console_output_to_utf8(std::string(buf, remaining)));
-                    truncated = true;
+        for (;;) {
+#if defined(_WIN32)
+            const int n = _read(_fileno(f), buf, (unsigned) sizeof(buf));
+#else
+            ssize_t n = read(fileno(f), buf, sizeof(buf));
+            while (n < 0 && errno == EINTR) {
+                n = read(fileno(f), buf, sizeof(buf));
+            }
+#endif
+            if (n <= 0) {
+                break;
+            }
+            if (truncated) {
+                continue;
+            }
+            const size_t len = (size_t) n;
+            if (output.size() + len <= max_output) {
+                output.append(buf, len);
+                if (on_chunk && !on_chunk(console_output_to_utf8(std::string(buf, len)))) {
+                    proc.terminate();
+                    break;
                 }
+            } else {
+                size_t remaining = max_output - output.size();
+                output.append(buf, remaining);
+                if (on_chunk && remaining > 0) on_chunk(console_output_to_utf8(std::string(buf, remaining)));
+                truncated = true;
             }
         }
     }
@@ -473,7 +513,7 @@ private:
     }
 };
 
-// timeout for auxiliary isolate calls (stat/mkdir/ls/cp helpers); exec_shell_command uses its own
+// timeout for auxiliary isolate calls (stat/mkdir/ls helpers); exec_shell_command uses its own
 // caller-controlled timeout instead, enforced separately in run()
 static constexpr int SERVER_TOOL_ISOLATE_EXEC_TIMEOUT = 15; // seconds
 static constexpr size_t SERVER_TOOL_ISOLATE_READ_FILE_MAX_SIZE = 64 * 1024 * 1024; // 64 MB
@@ -524,33 +564,12 @@ public:
     }
 
     bool write_file(const std::string & path, const std::string & content) const override {
-        std::string abs_path = resolve(path);
-
-        std::error_code ec;
-        fs::path tmp_dir = fs::temp_directory_path(ec);
-        if (ec) return false;
-
-        static std::atomic<uint64_t> tmp_counter{0};
-        fs::path tmp = tmp_dir / string_format(
-            "llama-tools-io-isolate-%zu-%llu.tmp",
-            std::hash<std::thread::id>{}(std::this_thread::get_id()),
-            (unsigned long long) tmp_counter.fetch_add(1));
-
-        {
-            std::ofstream f(tmp, std::ios::binary);
-            if (!f) return false;
-            f << content;
-            if (!f) return false;
-        }
-
-        bool ok = shell_run({"sh", "-c", "mkdir -p \"$(dirname \"$1\")\"", "_", abs_path});
-        if (ok) {
-            ok = upload(tmp.string(), abs_path);
-        }
-
-        std::error_code rm_ec;
-        fs::remove(tmp, rm_ec);
-        return ok;
+        // the content travels on stdin: no argv for the far side to re-parse, no temp file on the host
+        auto res = run_subprocess(
+            build_argv({"sh", "-c", "mkdir -p \"$(dirname \"$1\")\" && cat > \"$1\"", "_", resolve(path)},
+                       /*needs_stdin=*/true),
+            4096, SERVER_TOOL_ISOLATE_EXEC_TIMEOUT, nullptr, true, "", &content);
+        return res.exit_code == 0 && !res.timed_out;
     }
 
     list_result list_entries(const std::string & base, int max_depth, list_kind kind) const override {
@@ -612,9 +631,6 @@ protected:
     // a transport that re-parses its args in a remote shell (ssh) must join `inner` with shell_quote_join()
     virtual std::vector<std::string> build_argv(const std::vector<std::string> & inner, bool needs_stdin) const = 0;
 
-    // copy a host file into the isolate, `isolate_path` is absolute and its parent already exists
-    virtual bool upload(const std::string & host_path, const std::string & isolate_path) const = 0;
-
     // quote `argv` into a single string that a POSIX shell re-parses into exactly `argv`
     static std::string shell_quote_join(const std::vector<std::string> & argv) {
         std::string out;
@@ -634,7 +650,7 @@ protected:
 private:
     std::string cwd;
 
-    // set the working directory in the command itself, docker's `-w` has no equivalent on every transport
+    // set the working directory in the command itself, no `-w` equivalent exists on every transport
     // auxiliary calls do not need this, they use the absolute paths from resolve()
     std::vector<std::string> with_cwd(const std::vector<std::string> & inner) const {
         if (cwd.empty()) {
@@ -697,15 +713,16 @@ private:
     }
 };
 
-// an already-running docker container, driven through `docker exec` and `docker cp`
-class tools_io_docker : public tools_io_isolate {
+// an already-running container, driven through `<engine> exec`
+// docker and podman take the same verbs and the same argument order, so one class drives both
+class tools_io_container : public tools_io_isolate {
 public:
-    tools_io_docker(std::string container_id, std::string cwd = "")
-        : tools_io_isolate(std::move(cwd)), container_id(std::move(container_id)) {}
+    tools_io_container(std::string bin, std::string container_id, std::string cwd = "")
+        : tools_io_isolate(std::move(cwd)), bin(std::move(bin)), container_id(std::move(container_id)) {}
 
 protected:
     std::vector<std::string> build_argv(const std::vector<std::string> & inner, bool needs_stdin) const override {
-        std::vector<std::string> argv = {"docker", "exec"};
+        std::vector<std::string> argv = {bin, "exec"};
         if (needs_stdin) {
             argv.push_back("-i");
         }
@@ -714,30 +731,118 @@ protected:
         return argv;
     }
 
-    bool upload(const std::string & host_path, const std::string & isolate_path) const override {
-        auto res = run_subprocess(
-            {"docker", "cp", host_path, container_id + ":" + isolate_path},
-            4096, SERVER_TOOL_ISOLATE_EXEC_TIMEOUT, nullptr, true);
-        return res.exit_code == 0 && !res.timed_out;
-    }
-
 private:
+    std::string bin;
     std::string container_id;
 };
 
-// runtime spec used by --tools-runtime and the x-tool-runtime header
-// this is the only scheme for now, ssh: and podman: can be added next to it
-static const std::string SERVER_TOOL_RUNTIME_DOCKER_CONTAINER = "docker-container:";
+// a remote host reached over ssh
+// this is remoting, not isolation: the tools can do anything the target account can do
+class tools_io_ssh : public tools_io_isolate {
+public:
+    tools_io_ssh(std::string target, std::string cwd = "")
+        : tools_io_isolate(std::move(cwd)), target(std::move(target)) {}
+
+    // the target can come from a client header, and ssh reads options from its argv
+    // a target starting with '-' would become one, e.g. -oProxyCommand=<anything> runs on the host
+    static bool is_valid_target(const std::string & target) {
+        if (target.empty() || target[0] == '-') {
+            return false;
+        }
+        return std::all_of(target.begin(), target.end(), [](unsigned char c) {
+            return std::isalnum(c) || c == '.' || c == '-' || c == '_' || c == '@';
+        });
+    }
+
+protected:
+    std::vector<std::string> build_argv(const std::vector<std::string> & inner, bool needs_stdin) const override {
+        // the remote shell re-parses the command line, so `inner` travels as one quoted word
+        std::vector<std::string> argv = ssh_argv();
+        if (!needs_stdin) {
+            argv.push_back("-n");
+        }
+        argv.push_back(target);
+        argv.push_back(shell_quote_join(inner));
+        return argv;
+    }
+
+private:
+    std::string target;
+
+    // there is no console here, so a prompt would hang the tool call
+    // key-based auth only, and the admin must trust the host key beforehand
+    static std::vector<std::string> ssh_argv() {
+        return {
+            "ssh",
+            "-o", "BatchMode=yes",
+            "-o", "PasswordAuthentication=no",
+            "-o", "KbdInteractiveAuthentication=no",
+            "-o", "StrictHostKeyChecking=yes",
+        };
+    }
+};
+
+// "<engine>:<image>" spawns a container and owns it, "<engine>-container:<id>" attaches to one
+struct container_runtime_spec {
+    std::string bin;
+    std::string arg; // image name when spawning, container id when attaching
+    bool attach = false;
+
+    static bool parse(const std::string & spec, container_runtime_spec & out) {
+        // docker and podman take the same verbs, hence a single implementation
+        static const char * engines[] = {"docker", "podman"};
+        for (const char * bin : engines) {
+            const std::string attach_prefix = std::string(bin) + "-container:";
+            if (spec.rfind(attach_prefix, 0) == 0) {
+                out = {bin, spec.substr(attach_prefix.size()), true};
+                return true;
+            }
+            const std::string spawn_prefix = std::string(bin) + ":";
+            if (spec.rfind(spawn_prefix, 0) == 0) {
+                out = {bin, spec.substr(spawn_prefix.size()), false};
+                return true;
+            }
+        }
+        return false;
+    }
+
+    // same risk as the ssh target: an id starting with '-' would become an engine option,
+    // e.g. --privileged
+    static bool is_valid_id(const std::string & id) {
+        if (id.empty() || !std::isalnum((unsigned char) id[0])) {
+            return false;
+        }
+        return std::all_of(id.begin(), id.end(), [](unsigned char c) {
+            return std::isalnum(c) || c == '.' || c == '-' || c == '_';
+        });
+    }
+};
 
-// an empty runtime runs the tools on the host
 static std::unique_ptr<tools_io> make_tools_io(const json & params) {
     std::string cwd     = json_value(params, "cwd", std::string());
     std::string runtime = json_value(params, "runtime", std::string());
     if (runtime.empty()) {
+        // an empty runtime runs the tools on the host
         return std::make_unique<tools_io_basic>(cwd);
     }
-    if (runtime.rfind(SERVER_TOOL_RUNTIME_DOCKER_CONTAINER, 0) == 0) {
-        return std::make_unique<tools_io_docker>(runtime.substr(SERVER_TOOL_RUNTIME_DOCKER_CONTAINER.size()), cwd);
+    container_runtime_spec container;
+    if (container_runtime_spec::parse(runtime, container)) {
+        // spawning belongs to the runtime that owns the container, a tool call only attaches
+        if (!container.attach) {
+            throw std::runtime_error("tool runtime must name a running container: " + runtime);
+        }
+        if (!container_runtime_spec::is_valid_id(container.arg)) {
+            throw std::runtime_error("invalid container id: " + container.arg);
+        }
+        return std::make_unique<tools_io_container>(container.bin, container.arg, cwd);
+    }
+    const std::string ssh_prefix = "ssh:";
+    if (runtime.rfind(ssh_prefix, 0) == 0) {
+        std::string target = runtime.substr(ssh_prefix.size());
+        if (!tools_io_ssh::is_valid_target(target)) {
+            throw std::runtime_error("invalid ssh target: " + target);
+        }
+        return std::make_unique<tools_io_ssh>(target, cwd);
     }
     // do not fall back to the host, the caller asked for an isolate
     throw std::runtime_error("unknown tool runtime: " + runtime);
@@ -1769,81 +1874,82 @@ struct server_mcp_tool : server_tool {
     }
 };
 
-// owns the docker container used as the sandboxed runtime for tool invocations, as configured by
-// --tools-runtime. "spawned" mode starts and stops the container itself; "existing" mode just reuses
-// a container id the user already has running and never stops it.
-struct server_tools_docker_runtime {
-    server_tools_docker_runtime(const server_tools_docker_runtime &) = delete;
+// resolves --tools-runtime into the isolate that every tool call runs through
+// spec() returns the runtime string make_tools_io() takes, and runs once per tool call
+struct server_tools_runtime {
+    virtual ~server_tools_runtime() = default;
+    virtual std::string spec() = 0;
+};
 
-    explicit server_tools_docker_runtime(const std::string & spec) {
-        static const std::string docker_prefix = "docker:";
-        if (spec.rfind(docker_prefix, 0) == 0) {
-            spawned = true;
-            image   = spec.substr(docker_prefix.size());
-            if (image.empty()) {
-                throw std::runtime_error("--tools-runtime docker:<image> requires an image name");
-            }
-            spawn();
-        } else if (spec.rfind(SERVER_TOOL_RUNTIME_DOCKER_CONTAINER, 0) == 0) {
-            spawned      = false;
-            container_id = spec.substr(SERVER_TOOL_RUNTIME_DOCKER_CONTAINER.size());
-            if (container_id.empty()) {
-                throw std::runtime_error("--tools-runtime docker-container:<id> requires a container id");
-            }
-        } else {
+// a target that already exists and needs no lifecycle
+// the spec is validated once at startup, then passed straight through
+struct server_tools_static_runtime : server_tools_runtime {
+    explicit server_tools_static_runtime(std::string spec) : runtime_spec(std::move(spec)) {}
+    std::string spec() override { return runtime_spec; }
+
+private:
+    std::string runtime_spec;
+};
+
+// owns the container the tools run in, as set by --tools-runtime "<engine>:<image>"
+// it is spawned here and stopped when the server exits
+struct server_tools_container_runtime : server_tools_runtime {
+    server_tools_container_runtime(const server_tools_container_runtime &) = delete;
+
+    explicit server_tools_container_runtime(const std::string & spec) {
+        container_runtime_spec parsed;
+        if (!container_runtime_spec::parse(spec, parsed)) {
             throw std::runtime_error("unknown --tools-runtime option: " + spec);
         }
-    }
 
-    ~server_tools_docker_runtime() {
-        if (spawned && !container_id.empty()) {
-            // closing stdin signals the container's shell (its pid 1) to exit; --rm then removes it
-            proc.close_stdin();
-            proc.join();
+        bin   = parsed.bin;
+        image = parsed.arg;
+        if (image.empty()) {
+            throw std::runtime_error("--tools-runtime " + bin + ":<image> requires an image name");
         }
+        spawn();
     }
 
-    // container id to use for the next tool call; respawns a spawned container that died on its own,
-    // or throws if an externally-managed one is no longer reachable
-    std::string get_container_id() {
+    ~server_tools_container_runtime() override {
+        // closing stdin signals the container's shell (its pid 1) to exit; --rm then removes it
+        proc.close_stdin();
+        proc.join();
+    }
+
+    // respawns a container that died on its own, so the returned spec always names a running one
+    std::string spec() override {
         std::lock_guard<std::mutex> lock(mutex);
-        if (!spawned) {
-            if (!is_running(container_id)) {
-                throw std::runtime_error(string_format(
-                    "docker container \"%s\" is no longer running, restart it to keep using tools",
-                    container_id.c_str()));
-            }
-            return container_id;
-        }
-
         if (!proc.alive()) {
-            SRV_WRN("docker tools runtime container \"%s\" died, respawning\n", container_id.c_str());
+            SRV_WRN("%s tools runtime container \"%s\" died, respawning\n", bin.c_str(), container_id.c_str());
             spawn();
         }
-        return container_id;
+        return bin + "-container:" + container_id;
     }
 
 private:
-    bool spawned = false;
-    std::string image; // spawned mode only
+    std::string bin;
+    std::string image;
     std::string container_id;
-    common_subproc proc; // spawned mode only: `docker run` client that keeps the container alive
+    common_subproc proc; // `<engine> run` client that keeps the container alive
     std::mutex mutex;
 
-    // spawns "docker run --rm -i <image> sh" and keeps its stdin open; the shell blocks reading stdin,
+    // spawns "<engine> run --rm -i <image> sh" and keeps its stdin open; the shell blocks reading stdin,
     // so the container stays alive until we close it (see destructor) or it is killed from the outside
     void spawn() {
+        // create() writes over the handle it is given, so the previous one is released first
+        proc.join();
+
         std::error_code ec;
         fs::path cidfile = fs::temp_directory_path(ec) / string_format(
             "llama-tools-runtime-cid-%zu.tmp", std::hash<std::thread::id>{}(std::this_thread::get_id()));
         fs::remove(cidfile, ec);
 
-        std::vector<std::string> args = {"docker", "run", "--rm", "-i", "--cidfile", cidfile.string(), image, "sh"};
+        std::vector<std::string> args = {bin, "run", "--rm", "-i", "--cidfile", path_to_utf8(cidfile), image, "sh"};
         int options = subprocess_option_no_window
                     | subprocess_option_inherit_environment
                     | subprocess_option_search_user_path;
         if (!proc.create(args, options)) {
-            throw std::runtime_error("failed to spawn docker container for tools runtime (image: " + image + ")");
+            throw std::runtime_error("failed to spawn " + bin + " container for tools runtime (image: " + image + ")");
         }
 
         std::string cid;
@@ -1855,15 +1961,10 @@ private:
         fs::remove(cidfile, ec);
         if (cid.empty()) {
             proc.terminate();
-            throw std::runtime_error("timed out waiting for docker container to start (image: " + image + ")");
+            throw std::runtime_error("timed out waiting for " + bin + " container to start (image: " + image + ")");
         }
         container_id = cid;
     }
-
-    static bool is_running(const std::string & id) {
-        auto res = run_subprocess({"docker", "inspect", "-f", "{{.State.Running}}", id}, 16, 5, nullptr, true);
-        return res.exit_code == 0 && !res.timed_out && res.output.rfind("true", 0) == 0;
-    }
 };
 
 static server_tool & find_tool(std::vector<std::unique_ptr<server_tool>> & tools, const std::string & name, bool require_stream) {
@@ -1914,11 +2015,22 @@ static std::string get_header(const std::map<std::string, std::string> & headers
 server_tools::server_tools() = default;
 server_tools::~server_tools() = default;
 
+// the "<engine>:<image>" form owns a container lifecycle
+// anything else names an existing target, so only its spec is validated here at startup
+static std::unique_ptr<server_tools_runtime> make_tools_runtime(const std::string & spec) {
+    container_runtime_spec parsed;
+    if (container_runtime_spec::parse(spec, parsed) && !parsed.attach) {
+        return std::make_unique<server_tools_container_runtime>(spec);
+    }
+    make_tools_io({{"runtime", spec}}); // nothing to own, just reject a bad spec now
+    return std::make_unique<server_tools_static_runtime>(spec);
+}
+
 void server_tools::setup(const std::vector<std::string> & enabled_tools,
                          server_mcp & mcp_mgr,
                          const std::string & tools_runtime) {
     if (!tools_runtime.empty()) {
-        docker_runtime = std::make_unique<server_tools_docker_runtime>(tools_runtime);
+        runtime = make_tools_runtime(tools_runtime);
     }
 
     if (!enabled_tools.empty()) {
@@ -2016,11 +2128,11 @@ void server_tools::setup(const std::vector<std::string> & enabled_tools,
             if (params.contains("runtime")) {
                 params.erase("runtime");
             }
-            auto runtime = get_header(req.headers, "x-tool-runtime");
-            if (!runtime.empty()) {
-                params["runtime"] = runtime;
-            } else if (docker_runtime) {
-                params["runtime"] = SERVER_TOOL_RUNTIME_DOCKER_CONTAINER + docker_runtime->get_container_id();
+            auto runtime_header = get_header(req.headers, "x-tool-runtime");
+            if (!runtime_header.empty()) {
+                params["runtime"] = runtime_header;
+            } else if (runtime) {
+                params["runtime"] = runtime->spec();
             }
 
             server_tool & tool = find_tool(tools, tool_name, stream);

tools/server/server-tools.h

@@ -31,7 +31,7 @@ struct server_tool {
     json to_json() const;
 };
 
-struct server_tools_docker_runtime; // impl detail, defined in server-tools.cpp
+struct server_tools_runtime; // impl detail, defined in server-tools.cpp
 
 struct server_tools {
     std::vector<std::unique_ptr<server_tool>> tools;
@@ -40,8 +40,8 @@ struct server_tools {
     server_response queue_res;
     std::atomic<int> res_id{0};
 
-    // set when --tools-runtime is configured; owns the docker container used to run tools, if any
-    std::unique_ptr<server_tools_docker_runtime> docker_runtime;
+    // set when --tools-runtime is configured; routes every tool call through an isolate
+    std::unique_ptr<server_tools_runtime> runtime;
 
     void setup(const std::vector<std::string> & enabled_tools,
                server_mcp & mcp_mgr,

tools/server/server.cpp

@@ -89,7 +89,7 @@ int llama_server(int argc, char ** argv) {
     std::setlocale(LC_NUMERIC, "C");
 
 #ifndef _WIN32
-    // Ignore SIGPIPE so the server does not crash if an MCP child exits while we are writing to its stdin
+    // Ignore SIGPIPE so the server does not crash if a child (MCP server, tools runtime) exits while we are writing to its stdin
     signal(SIGPIPE, SIG_IGN);
 #endif
 

tools/server/tests/unit/test_tools_builtin.py

@@ -14,7 +14,7 @@ PROJECT_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..
 GREP_MARKER = "llama_cpp_test_tools_builtin_marker_grep_search"
 
 # image the container runtime tests run their shell in
-DOCKER_IMAGE = "busybox"
+CONTAINER_IMAGE = "busybox"
 
 
 @pytest.fixture(autouse=True)
@@ -151,54 +151,59 @@ def test_tools_builtin_cwd_header():
             os.remove(marker_path)
 
 
-def _docker_unavailable_reason() -> str | None:
-    """None if docker can run the image these tests use, otherwise the reason it can't."""
-    docker_bin = shutil.which("docker")
-    if docker_bin is None:
-        return "docker is not installed"
+def _container_engine_unavailable_reason(engine: str) -> str | None:
+    """None if `engine` can run the image these tests use, otherwise the reason it can't."""
+    engine_bin = shutil.which(engine)
+    if engine_bin is None:
+        return f"{engine} is not installed"
     try:
-        # a daemon that answers `docker info` still cannot run a linux image when it serves
-        # windows containers, so probe the image itself, which also pulls it before the tests
-        subprocess.run([docker_bin, "run", "--rm", DOCKER_IMAGE, "true"], capture_output=True, timeout=60, check=True)
+        # a daemon that answers `info` still cannot run a linux image when it serves windows
+        # containers, so probe the image itself, which also pulls it before the tests
+        subprocess.run([engine_bin, "run", "--rm", CONTAINER_IMAGE, "true"], capture_output=True, timeout=60, check=True)
     except Exception as e:
-        return f"docker cannot run {DOCKER_IMAGE}: {e}"
+        return f"{engine} cannot run {CONTAINER_IMAGE}: {e}"
     return None
 
 
-@pytest.fixture
-def docker_container():
-    reason = _docker_unavailable_reason()
+@pytest.fixture(params=["docker", "podman"])
+def container_engine(request):
+    engine = request.param
+    reason = _container_engine_unavailable_reason(engine)
     if reason is not None:
         pytest.skip(reason)  # ty: ignore[too-many-positional-arguments, invalid-argument-type]
+    return engine
 
+
+@pytest.fixture
+def container_id(container_engine: str):
     proc = subprocess.run(
-        ["docker", "run", "-d", "--rm", DOCKER_IMAGE, "sleep", "300"],
+        [container_engine, "run", "-d", "--rm", CONTAINER_IMAGE, "sleep", "300"],
         capture_output=True, text=True,
     )
     if proc.returncode != 0:
-        pytest.skip(f"failed to start docker container: {proc.stderr.strip()}")  # ty: ignore[too-many-positional-arguments, invalid-argument-type]
+        pytest.skip(f"failed to start {container_engine} container: {proc.stderr.strip()}")  # ty: ignore[too-many-positional-arguments, invalid-argument-type]
 
-    container_id = proc.stdout.strip()
+    cid = proc.stdout.strip()
     try:
-        yield container_id
+        yield cid
     finally:
-        subprocess.run(["docker", "rm", "-f", container_id], capture_output=True)
+        subprocess.run([container_engine, "rm", "-f", cid], capture_output=True)
 
 
-def test_tools_builtin_runtime_header(docker_container: str):
+def test_tools_builtin_runtime_header(container_engine: str, container_id: str):
     global server
     server.start()
 
-    headers = {"x-tool-runtime": f"docker-container:{docker_container}", "x-tool-cwd": "/tmp"}
+    headers = {"x-tool-runtime": f"{container_engine}-container:{container_id}", "x-tool-cwd": "/tmp"}
 
-    write_res = call_tool("write_file", {"path": "test.log", "content": "hello docker\n"}, headers=headers)
+    write_res = call_tool("write_file", {"path": "test.log", "content": "hello container\n"}, headers=headers)
     assert write_res["result"] == "file written successfully"
 
     read_res = call_tool("read_file", {"path": "test.log"}, headers=headers)
-    assert read_res["plain_text_response"] == "hello docker\n"
+    assert read_res["plain_text_response"] == "hello container\n"
 
     exec_res = call_tool("exec_shell_command", {"command": "cat test.log"}, headers=headers)
-    assert "hello docker" in exec_res["plain_text_response"]
+    assert "hello container" in exec_res["plain_text_response"]
 
 
 def test_tools_builtin_runtime_header_unknown_scheme():
@@ -208,18 +213,46 @@ def test_tools_builtin_runtime_header_unknown_scheme():
     # an unknown runtime must fail, never silently fall back to running on the host
     res = server.make_request("POST", "/tools",
                               data={"tool": "exec_shell_command", "params": {"command": "echo hi"}},
-                              headers={"x-tool-runtime": "ssh:example.com"})
+                              headers={"x-tool-runtime": "fake:does-not-exist"})
     assert res.status_code == 500, res.body
     assert "unknown tool runtime" in str(res.body)
 
 
+def test_tools_builtin_runtime_header_rejects_ssh_option_injection():
+    global server
+    server.start()
+
+    # ssh reads options from its argv, so a target starting with '-' must be rejected
+    res = server.make_request("POST", "/tools",
+                              data={"tool": "exec_shell_command", "params": {"command": "echo hi"}},
+                              headers={"x-tool-runtime": "ssh:-oProxyCommand=touch /tmp/pwned"})
+    assert res.status_code == 500, res.body
+    assert "invalid ssh target" in str(res.body)
+
+
+@pytest.mark.parametrize("engine", ["docker", "podman"])
+def test_tools_builtin_runtime_header_rejects_container_option_injection(engine: str):
+    global server
+    server.start()
+
+    # the container id lands on the `<engine> exec` command line, so an id that looks
+    # like an option must be rejected
+    res = server.make_request("POST", "/tools",
+                              data={"tool": "exec_shell_command", "params": {"command": "echo hi"}},
+                              headers={"x-tool-runtime": f"{engine}-container:--privileged"})
+    assert res.status_code == 500, res.body
+    assert "invalid container id" in str(res.body)
+
+
 def test_tools_builtin_docker_runtime_cleans_up_spawned_container():
-    reason = _docker_unavailable_reason()
+    # docker-only: this reads the container hostname to get the spawned id, which only docker
+    # sets to the short id. podman is covered by the attach path above
+    reason = _container_engine_unavailable_reason("docker")
     if reason is not None:
         pytest.skip(reason)  # ty: ignore[too-many-positional-arguments, invalid-argument-type]
 
     global server
-    server.server_tools_runtime = f"docker:{DOCKER_IMAGE}"
+    server.server_tools_runtime = f"docker:{CONTAINER_IMAGE}"
     server.start()
 
     # exec_shell_command runs inside the container spawned for --tools-runtime; docker sets

tools/ui/src/lib/components/app/chat/ChatForm/ChatFormContenteditable.svelte

@@ -797,7 +797,7 @@
 		data-placeholder={placeholder}
 		tabindex={disabled ? -1 : 0}
 		class={[
-			'chat-form-contenteditable text-md min-h-12 w-full whitespace-pre-wrap wrap-break-word border-0 bg-transparent p-0 leading-6 outline-none focus-visible:ring-0 focus-visible:ring-offset-0',
+			'chat-form-contenteditable text-md min-h-12 w-full overflow-y-auto whitespace-pre-wrap wrap-break-word border-0 bg-transparent p-0 leading-6 outline-none focus-visible:ring-0 focus-visible:ring-offset-0',
 			disabled && 'cursor-not-allowed'
 		]}
 		style="max-height: var(--max-message-height);"

tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageSystem/ChatMessageSystem.svelte

@@ -164,7 +164,7 @@
 								? `max-height: ${MAX_HEIGHT}px;`
 								: 'max-height: none;'}
 						>
-							{#if !currentConfig.renderContentAsRawText}
+							{#if currentConfig.renderUserContentAsMarkdown}
 								<div bind:this={messageElement} class={isExpanded ? 'cursor-text' : ''}>
 									<MarkdownContent class="markdown-system-content" content={message.content} />
 								</div>

tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageUser/ChatMessageUserBubble.svelte

@@ -1,5 +1,5 @@
 <script lang="ts">
-	import { ChatAttachmentsList, MarkdownContent } from '$lib/components/app';
+	import { ChatAttachmentsList, MarkdownContent, MentionText } from '$lib/components/app';
 	import { Card } from '$lib/components/ui/card';
 	import { config } from '$lib/stores/settings.svelte';
 	import type { DatabaseMessageExtra } from '$lib/types/database';
@@ -64,14 +64,14 @@
 		data-multiline={isMultiline ? '' : undefined}
 		style="{maxHeightStyle} overflow-wrap: anywhere; word-break: break-word;"
 	>
-		{#if renderMarkdown && !currentConfig.renderContentAsRawText}
+		{#if renderMarkdown && currentConfig.renderUserContentAsMarkdown}
 			<div bind:this={messageElement}>
 				<MarkdownContent class="markdown-user-content" {content} />
 			</div>
 		{:else}
-			<span bind:this={messageElement} class="text-md whitespace-pre-wrap">
-				{content}
-			</span>
+			<span bind:this={messageElement} class="text-md whitespace-pre-wrap"
+				><MentionText {content} /></span
+			>
 		{/if}
 	</Card>
 {/if}

tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessageReasoningBlock.svelte

@@ -140,7 +140,7 @@
 		class:is-streaming={isPending}
 		onscroll={handleScrollEvent}
 	>
-		{#if !currentConfig.renderContentAsRawText}
+		{#if currentConfig.renderThinkingAsMarkdown}
 			<MarkdownContent content={section.content} class="text-muted-foreground" {attachments} />
 		{:else}
 			<div

tools/ui/src/lib/components/app/content/MentionBadge.svelte

@@ -0,0 +1,36 @@
+<script lang="ts">
+	import { SETTINGS_KEYS } from '$lib/constants';
+	import { settingsStore } from '$lib/stores/settings.svelte';
+	import { toolsStore } from '$lib/stores/tools.svelte';
+	import {
+		getMentionBadgeIconPaths,
+		getMentionBadgeLabel,
+		MENTION_BADGE_CLASSNAME,
+		MENTION_BADGE_ICON_CLASSNAME,
+		MENTION_BADGE_SVG_ATTRIBUTES
+	} from '$lib/utils';
+
+	interface Props {
+		name: string;
+		path: string;
+	}
+
+	let { name, path }: Props = $props();
+
+	let showFullPath = $derived(
+		settingsStore.getConfig(SETTINGS_KEYS.SHOW_FULL_PATH_IN_MENTIONS) as boolean
+	);
+	let label = $derived(getMentionBadgeLabel(name, path, showFullPath, toolsStore.serverHome));
+</script>
+
+<!-- The chip is a flex container, so template whitespace between its
+     children collapses away and the icon keeps its `gap-1` spacing. -->
+<span class={MENTION_BADGE_CLASSNAME} title={path}>
+	<svg {...MENTION_BADGE_SVG_ATTRIBUTES} class={MENTION_BADGE_ICON_CLASSNAME}>
+		{#each getMentionBadgeIconPaths(path) as d (d)}
+			<path {d} />
+		{/each}
+	</svg>
+
+	<span class="shrink-0 truncate">{label}</span>
+</span>

tools/ui/src/lib/components/app/content/MentionText.svelte

@@ -0,0 +1,17 @@
+<script lang="ts">
+	import MentionBadge from './MentionBadge.svelte';
+	import { splitMentionSegments } from '$lib/utils';
+
+	interface Props {
+		content: string;
+	}
+
+	let { content }: Props = $props();
+
+	let segments = $derived(splitMentionSegments(content));
+</script>
+
+<!-- Segments sit in a `whitespace-pre-wrap` parent, so the markup stays
+     glued: any newline between the tags below would print as a space. -->
+<!-- prettier-ignore -->
+{#each segments as segment, index (index)}{#if segment.mention}<MentionBadge name={segment.mention.name} path={segment.mention.path} />{:else}{segment.text}{/if}{/each}

tools/ui/src/lib/components/app/content/index.ts

@@ -31,6 +31,20 @@
  */
 export { default as MarkdownContent } from './MarkdownContent/MarkdownContent.svelte';
 
+/**
+ * **MentionText** - Plain text with file mention badges
+ *
+ * Renders a message verbatim, turning only `[name](file://path)` links
+ * into the same badge chips the markdown path draws. Nothing else is
+ * interpreted, so pasted code keeps its `#` comments and underscores.
+ *
+ * @example
+ * ```svelte
+ * <span class="whitespace-pre-wrap"><MentionText content={message.content} /></span>
+ * ```
+ */
+export { default as MentionText } from './MentionText.svelte';
+
 /**
  * **SyntaxHighlightedCode** - Code syntax highlighting
  *

tools/ui/src/lib/constants/mention-badge.ts

@@ -10,6 +10,9 @@ export const MENTION_BADGE_CLASSNAME =
 
 export const MENTION_BADGE_ICON_CLASSNAME = 'h-3 w-3 shrink-0';
 
+/** Regex flag that makes the mention scanner walk every link in a message instead of the first. */
+export const MENTION_LINK_SCAN_FLAGS = 'g';
+
 /**
  * SVG attributes shared by the DOM-built and hast-built badge icons.
  * The tokenizer applies them via `setAttribute`, the rehype plugin

tools/ui/src/lib/constants/path-display.ts

@@ -12,6 +12,9 @@ import { UrlProtocol } from '$lib/enums';
 export const CWD_CHANGED_PREFIX = 'Set working directory to ';
 export const CWD_CLEARED_TEXT = 'Working directory cleared';
 
+/** Trailing separator that marks a path as a directory. */
+export const DIRECTORY_PATH_SUFFIX = '/';
+
 export const HOME_TILDE = '~';
 export const HOME_TILDE_PREFIX = '~/'; // tilde plus path separator
 

tools/ui/src/lib/constants/settings-keys.ts

@@ -41,7 +41,8 @@ export const SETTINGS_KEYS = {
 	// Performance
 	PRE_ENCODE_CONVERSATION: 'preEncodeConversation',
 	PRESENCE_PENALTY: 'presence_penalty',
-	RENDER_CONTENT_AS_RAW_TEXT: 'renderContentAsRawText',
+	RENDER_THINKING_AS_MARKDOWN: 'renderThinkingAsMarkdown',
+	RENDER_USER_CONTENT_AS_MARKDOWN: 'renderUserContentAsMarkdown',
 	// Penalties
 	REPEAT_LAST_N: 'repeat_last_n',
 	REPEAT_PENALTY: 'repeat_penalty',

tools/ui/src/lib/constants/settings-registry.ts

@@ -230,10 +230,18 @@ const SETTINGS_REGISTRY: Record<string, SettingsSectionEntry> = {
 				type: SettingsFieldType.CHECKBOX
 			},
 			{
-				defaultValue: false,
-				help: 'Display user, system and thinking content as plain text instead of formatted Markdown. Markdown is the default so that @-mention badges render in sent messages.',
-				key: SETTINGS_KEYS.RENDER_CONTENT_AS_RAW_TEXT,
-				label: 'Render content as raw text',
+				defaultValue: true,
+				help: 'Render user messages using markdown formatting in the chat. Turn this off to keep a message exactly as typed; @-mention badges show either way.',
+				key: SETTINGS_KEYS.RENDER_USER_CONTENT_AS_MARKDOWN,
+				label: 'Render user content as Markdown',
+				section: SETTINGS_SECTION_SLUGS.DISPLAY,
+				type: SettingsFieldType.CHECKBOX
+			},
+			{
+				defaultValue: true,
+				help: 'Render the reasoning/thinking block content as formatted Markdown instead of plain text.',
+				key: SETTINGS_KEYS.RENDER_THINKING_AS_MARKDOWN,
+				label: 'Render thinking as Markdown',
 				section: SETTINGS_SECTION_SLUGS.DISPLAY,
 				type: SettingsFieldType.CHECKBOX
 			},

tools/ui/src/lib/services/migration.service.ts

@@ -629,6 +629,37 @@ const configTypesMigration: Migration = {
 			console.log(`[Migration] Config types: coerced string booleans (changed=${changed})`);
 	}
 };
+const RENDER_KEYS_MIGRATION_ID = 'render-keys-unfold-v1';
+const LEGACY_RENDER_RAW_TEXT_KEY = 'renderContentAsRawText';
+const renderKeysMigration: Migration = {
+	description: 'Unfold the single raw text render toggle onto the per-surface render keys',
+	id: RENDER_KEYS_MIGRATION_ID,
+
+	async run(): Promise<void> {
+		const configRaw = localStorage.getItem(CONFIG_LOCALSTORAGE_KEY);
+
+		if (configRaw === null) return;
+
+		const config = JSON.parse(configRaw);
+
+		if (!(LEGACY_RENDER_RAW_TEXT_KEY in config)) return;
+
+		// The toggle carried user content and thinking at once and cannot say which surface
+		// was chosen, so it only restores the user key and thinking keeps its own default.
+		if (!(SETTINGS_KEYS.RENDER_USER_CONTENT_AS_MARKDOWN in config)) {
+			config[SETTINGS_KEYS.RENDER_USER_CONTENT_AS_MARKDOWN] =
+				config[LEGACY_RENDER_RAW_TEXT_KEY] !== true;
+		}
+
+		// Dropped rather than preserved: the two render keys and the toggle describe the same
+		// surfaces, so leaving it behind would let a stale value fight the restored one.
+		delete config[LEGACY_RENDER_RAW_TEXT_KEY];
+		localStorage.setItem(CONFIG_LOCALSTORAGE_KEY, JSON.stringify(config));
+
+		if (import.meta.env.DEV && import.meta.env.VITE_DEBUG)
+			console.log('[Migration] Render keys: unfolded the raw text toggle');
+	}
+};
 const MCP_DEFAULT_OVERRIDES_LEGACY_KEY = `${STORAGE_APP_NAME}.mcpDefaultServerOverrides`;
 const MCP_DEFAULT_OVERRIDES_MERGE_MIGRATION_ID = 'mcp-default-overrides-merge-v1';
 /**
@@ -722,7 +753,8 @@ const migrations: Migration[] = [
 	customJsonKeyMigration,
 	mcpDefaultEnabledMigration,
 	mcpDefaultOverridesMergeMigration,
-	configTypesMigration
+	configTypesMigration,
+	renderKeysMigration
 ];
 
 export const MigrationService = {

tools/ui/src/lib/stores/settings.svelte.ts

@@ -135,32 +135,6 @@ class SettingsStore {
 				...savedVal
 			};
 
-			// Migrate the legacy render keys into `renderContentAsRawText`
-			// (inverted semantics: the old keys opted INTO markdown). Any
-			// explicit raw-text preference wins when the legacy keys disagree.
-			const LEGACY_MARKDOWN_KEYS = ['renderUserContentAsMarkdown', 'renderThinkingAsMarkdown'];
-			const LEGACY_RAW_TEXT_KEY = 'renderUserContentAsRawText'; // this branch's intermediate key
-			const legacyKeys = [...LEGACY_MARKDOWN_KEYS, LEGACY_RAW_TEXT_KEY].filter(
-				(key) => key in savedVal
-			);
-
-			if (legacyKeys.length > 0) {
-				if (!(SETTINGS_KEYS.RENDER_CONTENT_AS_RAW_TEXT in savedVal)) {
-					if (LEGACY_RAW_TEXT_KEY in savedVal) {
-						this.config[SETTINGS_KEYS.RENDER_CONTENT_AS_RAW_TEXT] = savedVal[LEGACY_RAW_TEXT_KEY];
-					} else {
-						this.config[SETTINGS_KEYS.RENDER_CONTENT_AS_RAW_TEXT] = LEGACY_MARKDOWN_KEYS.filter(
-							(key) => key in savedVal
-						).some((key) => savedVal[key] === false);
-					}
-				}
-
-				for (const key of legacyKeys) {
-					delete (this.config as Record<string, unknown>)[key];
-				}
-				this.saveConfig();
-			}
-
 			// Default sendOnEnter to false on mobile when the user has no saved preference
 			if (!(SETTINGS_KEYS.SEND_ON_ENTER in savedVal)) {
 				if (isMobile.current) {

tools/ui/src/lib/utils/index.ts

@@ -240,6 +240,7 @@ export {
 	MENTION_BADGE_FOLDER_ICON_PATHS,
 	getMentionBadgeIconPaths,
 	getMentionBadgeLabel,
+	splitMentionSegments,
 	buildMentionInsertion
 } from './mention-badge';
 

tools/ui/src/lib/utils/mention-badge.ts

@@ -1,8 +1,9 @@
 import { abbreviateHome, lastPathSegment } from './path-display';
-import { FILE_URI_PREFIX } from '$lib/constants';
+import { DIRECTORY_PATH_SUFFIX, FILE_URI_PREFIX } from '$lib/constants';
 import {
 	MENTION_BADGE_FILE_ICON_PATHS,
-	MENTION_BADGE_FOLDER_ICON_PATHS
+	MENTION_BADGE_FOLDER_ICON_PATHS,
+	MENTION_LINK_SCAN_FLAGS
 } from '$lib/constants/mention-badge';
 import { FileMentionEntryType } from '$lib/enums';
 import type { FileMentionEntry } from '$lib/types';
@@ -48,8 +49,45 @@ export function decodeFileLinkPath(path: string): string {
 	}
 }
 
+export interface MentionTextSegment {
+	text: string;
+	mention: { name: string; path: string } | null;
+}
+
+/**
+ * Split raw text into plain runs and `[name](file://path)` mentions.
+ * The raw-text renderers walk these segments to draw badges without
+ * handing the message to the markdown parser, so a `#` stays a `#`.
+ */
+export function splitMentionSegments(value: string): MentionTextSegment[] {
+	const linkRe = fileMentionLinkRe(MENTION_LINK_SCAN_FLAGS);
+	const segments: MentionTextSegment[] = [];
+
+	let cursor = 0;
+	let match: RegExpExecArray | null;
+
+	while ((match = linkRe.exec(value)) !== null) {
+		if (match.index > cursor) {
+			segments.push({ mention: null, text: value.slice(cursor, match.index) });
+		}
+
+		segments.push({
+			mention: { name: match[1], path: decodeFileLinkPath(match[2]) },
+			text: match[0]
+		});
+
+		cursor = match.index + match[0].length;
+	}
+
+	if (cursor < value.length) segments.push({ mention: null, text: value.slice(cursor) });
+
+	return segments;
+}
+
 export function getMentionBadgeIconPaths(path: string): readonly string[] {
-	return path.endsWith('/') ? MENTION_BADGE_FOLDER_ICON_PATHS : MENTION_BADGE_FILE_ICON_PATHS;
+	return path.endsWith(DIRECTORY_PATH_SUFFIX)
+		? MENTION_BADGE_FOLDER_ICON_PATHS
+		: MENTION_BADGE_FILE_ICON_PATHS;
 }
 
 export function getMentionBadgeLabel(

tools/ui/tests/client/settings-raw-text-migration.svelte.test.ts

@@ -1,66 +0,0 @@
-// Guards the legacy render-key migration: `renderUserContentAsMarkdown`
-// and `renderThinkingAsMarkdown` (opt-INTO markdown) fold into the single
-// `renderContentAsRawText` setting, with any explicit raw-text preference
-// winning when the legacy keys disagree. Legacy keys are removed from the
-// persisted config so they do not stay orphaned in localStorage.
-
-import { CONFIG_LOCALSTORAGE_KEY } from '$lib/constants/storage';
-import { config, settingsStore } from '$lib/stores/settings.svelte';
-import { beforeEach, describe, expect, it } from 'vitest';
-
-function seedConfig(stored: Record<string, unknown>) {
-	localStorage.setItem(CONFIG_LOCALSTORAGE_KEY, JSON.stringify(stored));
-	settingsStore.initialize();
-}
-
-function persisted(): Record<string, unknown> {
-	return JSON.parse(localStorage.getItem(CONFIG_LOCALSTORAGE_KEY) ?? '{}');
-}
-
-describe('renderContentAsRawText migration', () => {
-	beforeEach(() => {
-		localStorage.removeItem(CONFIG_LOCALSTORAGE_KEY);
-		settingsStore.initialize();
-	});
-
-	it('maps renderUserContentAsMarkdown=false to raw text', () => {
-		seedConfig({ renderUserContentAsMarkdown: false });
-		expect(config().renderContentAsRawText).toBe(true);
-	});
-
-	it('maps renderUserContentAsMarkdown=true to markdown', () => {
-		seedConfig({ renderUserContentAsMarkdown: true });
-		expect(config().renderContentAsRawText).toBe(false);
-	});
-
-	it('maps renderThinkingAsMarkdown=false to raw text', () => {
-		seedConfig({ renderThinkingAsMarkdown: false });
-		expect(config().renderContentAsRawText).toBe(true);
-	});
-
-	it('lets any explicit raw-text preference win when the legacy keys disagree', () => {
-		seedConfig({ renderThinkingAsMarkdown: false, renderUserContentAsMarkdown: true });
-		expect(config().renderContentAsRawText).toBe(true);
-	});
-
-	it('honors the intermediate renderUserContentAsRawText key from the PR branch', () => {
-		seedConfig({ renderUserContentAsRawText: true });
-		expect(config().renderContentAsRawText).toBe(true);
-	});
-
-	it('keeps an already-migrated value and cleans up the legacy keys', () => {
-		seedConfig({ renderContentAsRawText: false, renderUserContentAsMarkdown: false });
-		expect(config().renderContentAsRawText).toBe(false);
-
-		const stored = persisted();
-
-		expect(stored.renderUserContentAsMarkdown).toBeUndefined();
-		expect(stored.renderThinkingAsMarkdown).toBeUndefined();
-		expect(stored.renderUserContentAsRawText).toBeUndefined();
-	});
-
-	it('defaults to markdown when no legacy key exists', () => {
-		seedConfig({});
-		expect(config().renderContentAsRawText).toBe(false);
-	});
-});

tools/ui/tests/client/settings-render-keys-migration.svelte.test.ts

@@ -0,0 +1,64 @@
+// Guards the unfolding of `renderContentAsRawText` back onto the two
+// per-surface render keys. The single toggle carried user content and
+// thinking at once, so only the user key is restored from it and thinking
+// returns to its own default. The toggle is removed from the persisted
+// config so it does not stay orphaned in localStorage.
+
+import { CONFIG_LOCALSTORAGE_KEY } from '$lib/constants/storage';
+import { MigrationService } from '$lib/services/migration.service';
+import { config, settingsStore } from '$lib/stores/settings.svelte';
+import { beforeEach, describe, expect, it } from 'vitest';
+
+const RENDER_KEYS_MIGRATION_ID = 'render-keys-unfold-v1';
+
+async function seedConfig(stored: Record<string, unknown>) {
+	localStorage.setItem(CONFIG_LOCALSTORAGE_KEY, JSON.stringify(stored));
+
+	const migration = MigrationService.getMigrations().find((m) => m.id === RENDER_KEYS_MIGRATION_ID);
+
+	await migration?.run();
+	settingsStore.initialize();
+}
+
+function persisted(): Record<string, unknown> {
+	return JSON.parse(localStorage.getItem(CONFIG_LOCALSTORAGE_KEY) ?? '{}');
+}
+
+describe('renderContentAsRawText unfolding', () => {
+	beforeEach(() => {
+		localStorage.removeItem(CONFIG_LOCALSTORAGE_KEY);
+		MigrationService.resetState();
+		settingsStore.initialize();
+	});
+
+	it('maps raw text to user content as plain text', async () => {
+		await seedConfig({ renderContentAsRawText: true });
+		expect(config().renderUserContentAsMarkdown).toBe(false);
+	});
+
+	it('maps markdown to user content as markdown', async () => {
+		await seedConfig({ renderContentAsRawText: false });
+		expect(config().renderUserContentAsMarkdown).toBe(true);
+	});
+
+	it('leaves thinking on its own default', async () => {
+		await seedConfig({ renderContentAsRawText: true });
+		expect(config().renderThinkingAsMarkdown).toBe(true);
+	});
+
+	it('keeps an explicit user preference over the toggle', async () => {
+		await seedConfig({ renderContentAsRawText: true, renderUserContentAsMarkdown: true });
+		expect(config().renderUserContentAsMarkdown).toBe(true);
+	});
+
+	it('drops the toggle from the persisted config', async () => {
+		await seedConfig({ renderContentAsRawText: true });
+		expect(persisted().renderContentAsRawText).toBeUndefined();
+	});
+
+	it('leaves both surfaces on markdown when nothing is stored', async () => {
+		await seedConfig({});
+		expect(config().renderUserContentAsMarkdown).toBe(true);
+		expect(config().renderThinkingAsMarkdown).toBe(true);
+	});
+});

tools/ui/tests/unit/mention-segments.test.ts

@@ -0,0 +1,48 @@
+import { splitMentionSegments } from '$lib/utils/mention-badge';
+import { describe, expect, it } from 'vitest';
+
+describe('splitMentionSegments', () => {
+	it('returns a single plain run when there is no mention', () => {
+		const segments = splitMentionSegments('# not a heading here');
+
+		expect(segments).toEqual([{ mention: null, text: '# not a heading here' }]);
+	});
+
+	it('splits text around a mention', () => {
+		const segments = splitMentionSegments('look at [main.c](file:///src/main.c) please');
+
+		expect(segments.map((segment) => segment.text)).toEqual([
+			'look at ',
+			'[main.c](file:///src/main.c)',
+			' please'
+		]);
+		expect(segments[1].mention).toEqual({ name: 'main.c', path: '/src/main.c' });
+	});
+
+	it('decodes percent-encoded paths', () => {
+		const segments = splitMentionSegments('[a b.txt](file:///tmp/a%20b.txt)');
+
+		expect(segments[0].mention?.path).toBe('/tmp/a b.txt');
+	});
+
+	it('keeps the directory marker so the folder icon is picked', () => {
+		const segments = splitMentionSegments('[src](file:///repo/src/)');
+
+		expect(segments[0].mention?.path).toBe('/repo/src/');
+	});
+
+	it('handles adjacent mentions with no text between them', () => {
+		const segments = splitMentionSegments('[a](file:///a)[b](file:///b)');
+
+		expect(segments).toHaveLength(2);
+		expect(segments.every((segment) => segment.mention !== null)).toBe(true);
+	});
+
+	it('preserves the exact source when segments are joined back', () => {
+		const source = 'see [a](file:///a) and [b](file:///b/) done';
+
+		expect(splitMentionSegments(source).reduce((acc, segment) => acc + segment.text, '')).toBe(
+			source
+		);
+	});
+});

vendor/cpp-httplib/httplib.h

@@ -8,8 +8,8 @@
 #ifndef CPPHTTPLIB_HTTPLIB_H
 #define CPPHTTPLIB_HTTPLIB_H
 
-#define CPPHTTPLIB_VERSION "0.52.0"
-#define CPPHTTPLIB_VERSION_NUM "0x003400"
+#define CPPHTTPLIB_VERSION "0.53.0"
+#define CPPHTTPLIB_VERSION_NUM "0x003500"
 
 #ifdef _WIN32
 #if defined(_WIN32_WINNT) && _WIN32_WINNT < 0x0A00
@@ -1805,6 +1805,7 @@ enum class Error {
   HTTPParsing,
   InvalidRangeHeader,
   UnsupportedContentEncoding,
+  WebSocketHandshake,
 
   // For internal use only
   SSLPeerCouldBeClosed_,
@@ -3233,8 +3234,6 @@ private:
   // Used to keep custom CA configuration exclusive with system CA loading.
   bool ca_cert_store_set_ = false;
 
-  long verify_result_ = 0;
-
   std::function<SSLVerifierResponse(tls::session_t)> session_verifier_;
 
 #ifdef CPPHTTPLIB_WINDOWS_AUTOMATIC_ROOT_CERTIFICATES_UPDATE
@@ -4204,6 +4203,50 @@ enum class CloseStatus : uint16_t {
 
 enum ReadResult : int { Fail = 0, Text = 1, Binary = 2 };
 
+// Result of WebSocketClient::connect(). Truthy only when the WebSocket
+// upgrade handshake fully succeeded. On failure error() identifies the
+// failing layer; status()/headers() expose the server's upgrade response
+// when one was received (status() is -1 otherwise).
+class Result {
+public:
+  Result() = default;
+  Result(Error err, int status, Headers &&headers)
+      : err_(err), status_(status), headers_(std::move(headers)) {}
+
+  explicit operator bool() const { return err_ == Error::Success; }
+  Error error() const { return err_; }
+
+  // Upgrade response info
+  int status() const { return status_; }
+  const Headers &headers() const { return headers_; }
+  std::string get_header_value(const std::string &key,
+                               const char *def = "") const {
+    return detail::get_header_value(headers_, key, def, 0);
+  }
+  bool has_header(const std::string &key) const {
+    return headers_.find(key) != headers_.end();
+  }
+
+#ifdef CPPHTTPLIB_SSL_ENABLED
+  Result(Error err, int status, Headers &&headers, int ssl_error,
+         uint64_t ssl_backend_error)
+      : err_(err), status_(status), headers_(std::move(headers)),
+        ssl_error_(ssl_error), ssl_backend_error_(ssl_backend_error) {}
+
+  int ssl_error() const { return ssl_error_; }
+  uint64_t ssl_backend_error() const { return ssl_backend_error_; }
+#endif
+
+private:
+  Error err_ = Error::Unknown; // a default-constructed Result is falsy
+  int status_ = -1;
+  Headers headers_;
+#ifdef CPPHTTPLIB_SSL_ENABLED
+  int ssl_error_ = 0;
+  uint64_t ssl_backend_error_ = 0;
+#endif
+};
+
 class WebSocket {
 public:
   WebSocket(const WebSocket &) = delete;
@@ -4270,7 +4313,7 @@ public:
 
   bool is_valid() const;
 
-  bool connect();
+  Result connect();
   ReadResult read(std::string &msg);
   bool send(const std::string &data);
   bool send(const char *data, size_t len);
@@ -4279,28 +4322,52 @@ public:
   bool is_open() const;
   const std::string &subprotocol() const;
   void set_read_timeout(time_t sec, time_t usec = 0);
+  template <class Rep, class Period>
+  void set_read_timeout(const std::chrono::duration<Rep, Period> &duration);
+
   void set_write_timeout(time_t sec, time_t usec = 0);
+  template <class Rep, class Period>
+  void set_write_timeout(const std::chrono::duration<Rep, Period> &duration);
+
   void set_websocket_ping_interval(time_t sec);
   void set_websocket_max_missed_pongs(int count);
   void set_tcp_nodelay(bool on);
   void set_address_family(int family);
   void set_ipv6_v6only(bool on);
   void set_socket_options(SocketOptions socket_options);
+
   void set_connection_timeout(time_t sec, time_t usec = 0);
+  template <class Rep, class Period>
+  void
+  set_connection_timeout(const std::chrono::duration<Rep, Period> &duration);
+
   void set_interface(const std::string &intf);
   void set_hostname_addr_map(std::map<std::string, std::string> addr_map);
 
 #ifdef CPPHTTPLIB_SSL_ENABLED
-  void set_ca_cert_path(const std::string &path);
+  struct PemMemory {
+    const char *cert_pem;
+    size_t cert_pem_len;
+    const char *key_pem;
+    size_t key_pem_len;
+    const char *private_key_password;
+  };
+  explicit WebSocketClient(const std::string &scheme_host_port_path,
+                           const PemMemory &pem, const Headers &headers = {});
+
+  void set_ca_cert_path(const std::string &ca_cert_file_path,
+                        const std::string &ca_cert_dir_path = std::string());
   void set_ca_cert_store(tls::ca_store_t store);
   void load_ca_cert_store(const char *ca_cert, std::size_t size);
   void enable_server_certificate_verification(bool enabled);
+  void enable_server_hostname_verification(bool enabled);
   void enable_system_ca(bool enabled);
 #endif
 
 private:
   void shutdown_and_close();
-  bool create_stream(std::unique_ptr<Stream> &strm);
+  bool create_stream(std::unique_ptr<Stream> &strm, Error &error,
+                     int &ssl_error, uint64_t &ssl_backend_error);
   void prepare_default_headers(Request &req);
 
   std::string host_;
@@ -4335,13 +4402,37 @@ private:
   tls::ctx_t tls_ctx_ = nullptr;
   tls::session_t tls_session_ = nullptr;
   std::string ca_cert_file_path_;
+  std::string ca_cert_dir_path_;
   bool custom_ca_loaded_ = false;
   bool certs_loaded_ = false;
   SystemCAMode system_ca_mode_ = SystemCAMode::Auto;
   bool server_certificate_verification_ = true;
+  bool server_hostname_verification_ = true;
 #endif
 };
 
+template <class Rep, class Period>
+inline void WebSocketClient::set_read_timeout(
+    const std::chrono::duration<Rep, Period> &duration) {
+  detail::duration_to_sec_and_usec(
+      duration, [&](time_t sec, time_t usec) { set_read_timeout(sec, usec); });
+}
+
+template <class Rep, class Period>
+inline void WebSocketClient::set_write_timeout(
+    const std::chrono::duration<Rep, Period> &duration) {
+  detail::duration_to_sec_and_usec(
+      duration, [&](time_t sec, time_t usec) { set_write_timeout(sec, usec); });
+}
+
+template <class Rep, class Period>
+inline void WebSocketClient::set_connection_timeout(
+    const std::chrono::duration<Rep, Period> &duration) {
+  detail::duration_to_sec_and_usec(duration, [&](time_t sec, time_t usec) {
+    set_connection_timeout(sec, usec);
+  });
+}
+
 namespace impl {
 
 bool is_valid_utf8(const std::string &s);

vendor/sheredom/patch-bsd.patch

@@ -1,19 +0,0 @@
-Fix build on NetBSD, which provides posix_spawn_file_actions_addchdir()
-but not the _np() variant.
-
-Upstream PR: https://github.com/sheredom/subprocess.h/pull/102
-Applied locally by scripts/sync_vendor.py until it is merged upstream.
-
-diff --git a/subprocess.h b/subprocess.h
-index 5e809023a4..74a4e006c7 100644
---- a/subprocess.h
-+++ b/subprocess.h
-@@ -1205,7 +1205,7 @@ cleanup:
- 
-   // Set working directory
-   if (process_cwd) {
--#if defined(__APPLE__) && MAC_OS_X_VERSION_MIN_REQUIRED >= 260000
-+#if defined(__NetBSD__) || (defined(__APPLE__) && MAC_OS_X_VERSION_MIN_REQUIRED >= 260000)
-     posix_error = posix_spawn_file_actions_addchdir(&actions, process_cwd);
- #else
- #if defined(__APPLE__) && defined(__clang__)

vendor/sheredom/patch-glibc-older-than-2.29.patch

@@ -1,47 +0,0 @@
-Fix building against glibc older than 2.29, which has no
-posix_spawn_file_actions_addchdir_np (the symbol is genuinely absent from
-libc.so, so no feature-test macro helps). Affects manylinux2014 (glibc 2.17)
-and manylinux_2_28, and was reported on RHEL 8.1. A requested process_cwd now
-fails with ENOSYS there instead of failing the build.
-
-Upstream PR: https://github.com/sheredom/subprocess.h/pull/104
-Applied locally by scripts/sync_vendor.py until it is merged upstream.
-
-(the README.md and test/ changes from the PR are omitted, we only vendor
-subprocess.h; rebased on top of patch-bsd.patch, so apply it after that one)
-
-diff --git a/subprocess.h b/subprocess.h
-index 1ef424a..c363393 100644
---- a/subprocess.h
-+++ b/subprocess.h
-@@ -274,6 +274,21 @@ subprocess_weak int subprocess_alive(struct subprocess_s *const process);
- #include <unistd.h>
- #endif
- 
-+/* Whether subprocess_create_ex can honour process_cwd. glibc only gained
-+   posix_spawn_file_actions_addchdir_np in 2.29. Define this yourself to
-+   override the detection, for instance on musl older than 1.1.24. */
-+#if !defined(SUBPROCESS_HAVE_CWD)
-+#if defined(__GLIBC__)
-+#if __GLIBC_PREREQ(2, 29)
-+#define SUBPROCESS_HAVE_CWD 1
-+#else
-+#define SUBPROCESS_HAVE_CWD 0
-+#endif
-+#else
-+#define SUBPROCESS_HAVE_CWD 1
-+#endif
-+#endif
-+
- #if defined(_WIN32)
- 
- #include <wchar.h>
-@@ -1219,6 +1234,8 @@ cleanup:
-   if (process_cwd) {
- #if defined(__NetBSD__) || (defined(__APPLE__) && MAC_OS_X_VERSION_MIN_REQUIRED >= 260000)
-     posix_error = posix_spawn_file_actions_addchdir(&actions, process_cwd);
-+#elif !SUBPROCESS_HAVE_CWD
-+    posix_error = ENOSYS;
- #else
- #if defined(__APPLE__) && defined(__clang__)
- #pragma clang diagnostic push

vendor/sheredom/patch-windows-quote-backslash.patch

@@ -1,107 +0,0 @@
-Fix Windows command line quoting of backslash runs: a trailing backslash, or
-backslashes preceding a double quote, were not doubled, so CommandLineToArgvW
-in the child parsed them as escapes and mangled the argument list.
-
-Upstream PR: https://github.com/sheredom/subprocess.h/pull/101
-Applied locally by scripts/sync_vendor.py until it is merged upstream.
-
-(the test/ changes from the PR are omitted, we only vendor subprocess.h)
-
-diff --git a/subprocess.h b/subprocess.h
-index 5e80902..b06ad4d 100644
---- a/subprocess.h
-+++ b/subprocess.h
-@@ -653,6 +653,7 @@ int subprocess_create_ex(const char *const commandLine[], int options,
-   int wide_len;
-   int i, j;
-   int need_quoting;
-+  subprocess_size_t bs_run;
-   unsigned long flags = 0;
-   unsigned long last_error = 0;
-   int result = subprocess_error_unknown;
-@@ -906,25 +907,29 @@ int subprocess_create_ex(const char *const commandLine[], int options,
-     len++;
- 
-     // Quote the argument if it has a space in it
--    if (strpbrk(commandLine[i], "\t\v ") != SUBPROCESS_NULL ||
--        commandLine[i][0] == SUBPROCESS_NULL)
-+    need_quoting = strpbrk(commandLine[i], "\t\v ") != SUBPROCESS_NULL ||
-+                   commandLine[i][0] == SUBPROCESS_NULL;
-+    if (need_quoting)
-       len += 2;
- 
-+    bs_run = 0;
-     for (j = 0; '\0' != commandLine[i][j]; j++) {
--      switch (commandLine[i][j]) {
--      default:
--        break;
--      case '\\':
--        if (commandLine[i][j + 1] == '"') {
--          len++;
--        }
-+      len++;
- 
--        break;
--      case '"':
--        len++;
--        break;
-+      if ('\\' == commandLine[i][j]) {
-+        bs_run++;
-+      } else {
-+        if ('"' == commandLine[i][j]) {
-+          // Duplicate the preceding run and escape the quote.
-+          len += bs_run + 1;
-+        }
-+        bs_run = 0;
-       }
--      len++;
-+    }
-+
-+    if (need_quoting) {
-+      // Duplicate trailing slashes before the generated closing quote.
-+      len += bs_run;
-     }
-   }
- 
-@@ -949,22 +954,29 @@ int subprocess_create_ex(const char *const commandLine[], int options,
-       commandLineCombined[len++] = '"';
-     }
- 
--    for (j = 0; '\0' != commandLine[i][j]; j++) {
--      switch (commandLine[i][j]) {
--      default:
--        break;
--      case '\\':
--        if (commandLine[i][j + 1] == '"') {
--          commandLineCombined[len++] = '\\';
--        }
-+    for (j = 0; '\0' != commandLine[i][j];) {
-+      bs_run = 0;
-+      while ('\\' == commandLine[i][j]) {
-+        bs_run++;
-+        j++;
-+      }
-+
-+      if ('"' == commandLine[i][j]) {
-+        // 2n + 1 slashes preserve n slashes and escape the quote.
-+        bs_run = (bs_run * 2) + 1;
-+      } else if ('\0' == commandLine[i][j] && need_quoting) {
-+        // 2n slashes preserve n slashes before the closing quote.
-+        bs_run *= 2;
-+      }
- 
--        break;
--      case '"':
-+      while (bs_run > 0) {
-         commandLineCombined[len++] = '\\';
--        break;
-+        bs_run--;
-       }
- 
--      commandLineCombined[len++] = commandLine[i][j];
-+      if ('\0' != commandLine[i][j]) {
-+        commandLineCombined[len++] = commandLine[i][j++];
-+      }
-     }
-     if (need_quoting) {
-       commandLineCombined[len++] = '"';

vendor/sheredom/subprocess.h

@@ -107,7 +107,8 @@ enum subprocess_error_e {
   subprocess_error_permission_denied = -5,
   subprocess_error_no_memory = -6,
   subprocess_error_pipe = -7,
-  subprocess_error_spawn = -8
+  subprocess_error_spawn = -8,
+  subprocess_error_not_supported = -9
 };
 
 #if defined(__cplusplus)
@@ -275,8 +276,10 @@ subprocess_weak int subprocess_alive(struct subprocess_s *const process);
 #endif
 
 /* Whether subprocess_create_ex can honour process_cwd. glibc only gained
-   posix_spawn_file_actions_addchdir_np in 2.29. Define this yourself to
-   override the detection, for instance on musl older than 1.1.24. */
+   posix_spawn_file_actions_addchdir_np in 2.29, and macOS in 10.15; the SDKs
+   mark it unavailable on iOS, tvOS and watchOS, where the undefined version
+   macro folds to 0 and so answers correctly. Define this yourself to override
+   the detection, for instance on musl older than 1.1.24. */
 #if !defined(SUBPROCESS_HAVE_CWD)
 #if defined(__GLIBC__)
 #if __GLIBC_PREREQ(2, 29)
@@ -284,11 +287,27 @@ subprocess_weak int subprocess_alive(struct subprocess_s *const process);
 #else
 #define SUBPROCESS_HAVE_CWD 0
 #endif
+#elif defined(__APPLE__) && MAC_OS_X_VERSION_MIN_REQUIRED < 101500
+#define SUBPROCESS_HAVE_CWD 0
 #else
 #define SUBPROCESS_HAVE_CWD 1
 #endif
 #endif
 
+/* Whether posix_spawn reports a failed exec back to the caller. glibc only
+   started doing so in 2.24; before that the child silently exits with 127. */
+#if !defined(SUBPROCESS_SPAWN_REPORTS_EXEC_ERRORS)
+#if defined(__GLIBC__)
+#if __GLIBC_PREREQ(2, 24)
+#define SUBPROCESS_SPAWN_REPORTS_EXEC_ERRORS 1
+#else
+#define SUBPROCESS_SPAWN_REPORTS_EXEC_ERRORS 0
+#endif
+#else
+#define SUBPROCESS_SPAWN_REPORTS_EXEC_ERRORS 1
+#endif
+#endif
+
 #if defined(_WIN32)
 
 #include <wchar.h>
@@ -554,6 +573,8 @@ int subprocess_error_from_errno(int error) {
   case ENFILE:
   case ENOMEM:
     return subprocess_error_no_memory;
+  case ENOSYS:
+    return subprocess_error_not_supported;
   default:
     return subprocess_error_unknown;
   }
@@ -1358,6 +1379,17 @@ cleanup:
       goto cleanup;
     }
   } else {
+#if !SUBPROCESS_SPAWN_REPORTS_EXEC_ERRORS
+    /* posix_spawn cannot tell us the exec failed, so check up front */
+    if (0 != access(commandLine[0], X_OK)) {
+      saved_errno = errno;
+      result = subprocess_error_from_errno(saved_errno);
+      if (subprocess_error_unknown == result) {
+        result = subprocess_error_spawn;
+      }
+      goto cleanup;
+    }
+#endif
     posix_error = posix_spawn(&child, commandLine[0], &actions,
                               SUBPROCESS_NULL,
                               SUBPROCESS_CONST_CAST(char *const *, commandLine),