Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	common/download.cpp
#	docs/backend/OPENVINO.md
#	docs/backend/snapdragon/CMakeUserPresets.json
#	docs/backend/snapdragon/README.md
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/argsort-ops.c
#	ggml/src/ggml-hexagon/htp/binary-ops.c
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-hexagon/htp/cumsum-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/get-rows-ops.c
#	ggml/src/ggml-hexagon/htp/hex-utils.h
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-ops.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/htp_iface.idl
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/repeat-ops.c
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	ggml/src/ggml-hexagon/htp/set-rows-ops.c
#	ggml/src/ggml-hexagon/htp/softmax-ops.c
#	ggml/src/ggml-hexagon/htp/ssm-conv.c
#	ggml/src/ggml-hexagon/htp/sum-rows-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl
#	models/templates/google-gemma-4-31B-it-interleaved.jinja
#	models/templates/google-gemma-4-31B-it.jinja
#	scripts/snapdragon/adb/run-bench.sh
#	scripts/snapdragon/adb/run-cli.sh
#	scripts/snapdragon/adb/run-completion.sh
#	scripts/snapdragon/adb/run-tool.sh
#	scripts/snapdragon/windows/run-bench.ps1
#	scripts/snapdragon/windows/run-cli.ps1
#	scripts/snapdragon/windows/run-mtmd.ps1
#	scripts/snapdragon/windows/run-tool.ps1
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tools/llama-bench/llama-bench.cpp
This commit is contained in:
Concedo
2026-04-11 11:19:32 +08:00
parent a165a73120 b136b62cf9
commit 4c860ae4ae
33 changed files with 13359 additions and 413 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/chat.cpp
+28 -8
View File
@@ -880,9 +880,10 @@ static common_chat_params common_chat_params_init_ministral_3(const common_chat_
adjusted_messages.push_back(adjusted);
}
auto has_tools = inputs.tools.is_array() && !inputs.tools.empty();
auto extract_reasoning = inputs.reasoning_format != COMMON_REASONING_FORMAT_NONE;
auto include_grammar = true;
auto has_tools = inputs.tools.is_array() && !inputs.tools.empty();
auto has_response_format = inputs.json_schema.is_object() && !inputs.json_schema.empty();
auto extract_reasoning = inputs.reasoning_format != COMMON_REASONING_FORMAT_NONE;
auto include_grammar = true;
data.supports_thinking = true;
data.thinking_start_tag = "[THINK]";
@@ -902,7 +903,7 @@ static common_chat_params common_chat_params_init_ministral_3(const common_chat_
extract_reasoning ? p.optional("[THINK]" + p.reasoning(p.until("[/THINK]")) + "[/THINK]") : p.eps();
// Response format parser
if (inputs.json_schema.is_object() && !inputs.json_schema.empty()) {
if (has_response_format) {
// Ministral wants to emit json surrounded by code fences
return generation_prompt + (reasoning << "```json" << p.content(p.schema(p.json(), "response-format", inputs.json_schema)) << "```");
}
@@ -943,6 +944,10 @@ static common_chat_params common_chat_params_init_ministral_3(const common_chat_
auto schema = function.at("parameters");
builder.resolve_refs(schema);
});
if (has_response_format) {
auto schema = inputs.json_schema;
builder.resolve_refs(schema);
}
parser.build_grammar(builder, data.grammar_lazy);
});
@@ -1078,6 +1083,10 @@ static common_chat_params common_chat_params_init_gpt_oss(const common_chat_temp
auto schema = function.at("parameters");
builder.resolve_refs(schema);
});
if (has_response_format) {
auto schema = inputs.json_schema;
builder.resolve_refs(schema);
}
parser.build_grammar(builder, data.grammar_lazy);
});
@@ -1098,7 +1107,9 @@ static common_chat_params common_chat_params_init_gemma4(const common_chat_templ
data.prompt = common_chat_template_direct_apply_impl(tmpl, inputs);
data.format = COMMON_CHAT_FORMAT_PEG_GEMMA4;
data.supports_thinking = true;
data.supports_thinking = true;
data.thinking_start_tag = "<|channel>thought";
data.thinking_end_tag = "<channel|>";
data.preserved_tokens = {
"<|channel>",
@@ -1117,9 +1128,9 @@ static common_chat_params common_chat_params_init_gemma4(const common_chat_templ
auto start = p.rule("start", p.prefix(inputs.generation_prompt, "<|channel>"));
if (extract_reasoning) {
p.rule("thought", p.literal("<|channel>thought\n") + p.reasoning(p.until("<channel|>")) + p.literal("<channel|>"));
p.rule("thought", p.literal("<|channel>thought") + p.space() + p.reasoning(p.until("<channel|>")) + p.literal("<channel|>"));
} else {
p.rule("thought", p.content(p.literal("<|channel>thought\n") + p.until("<channel|>") + p.literal("<channel|>")));
p.rule("thought", p.content(p.literal("<|channel>thought") + p.space() + p.until("<channel|>") + p.literal("<channel|>")));
}
auto thought = (p.peek(p.literal("<|channel>")) + p.ref("thought")) | p.negate(p.literal("<|channel>"));
@@ -1206,6 +1217,10 @@ static common_chat_params common_chat_params_init_gemma4(const common_chat_templ
auto schema = function.at("parameters");
builder.resolve_refs(schema);
});
if (has_response_format) {
auto schema = inputs.json_schema;
builder.resolve_refs(schema);
}
parser.build_grammar(builder, data.grammar_lazy);
});
@@ -1929,7 +1944,12 @@ std::optional<common_chat_params> common_chat_try_specialized_template(
// Gemma4 format detection
if (src.find("'<|tool_call>call:'") != std::string::npos) {
workaround::convert_tool_responses_gemma4(params.messages);
if (src.find("{#- OpenAI Chat Completions:") == std::string::npos) {
// apply workarounds if using the older gemma4 templates
LOG_WRN("%s: detected an outdated gemma4 chat template, applying compatibility workarounds. "
"Consider updating to the official template.\n", __func__);
workaround::convert_tool_responses_gemma4(params.messages);
}
return common_chat_params_init_gemma4(tmpl, params);
}