Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/cpu.Dockerfile
#	.devops/cuda.Dockerfile
#	.devops/intel.Dockerfile
#	.devops/musa.Dockerfile
#	.devops/openvino.Dockerfile
#	.devops/rocm.Dockerfile
#	.devops/vulkan.Dockerfile
#	.devops/zendnn.Dockerfile
#	.github/workflows/build-webgpu.yml
#	.github/workflows/release.yml
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/binary.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/concat.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/scale.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-mtmd-c-api.c
#	tools/cli/cli.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo
2026-06-10 17:21:05 +08:00
parent 258ca8fd90 e25a32e98c
commit afc8de2c6b
55 changed files with 1514 additions and 185 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-arch.cpp
+4
View File
@@ -559,6 +559,8 @@ static const std::map<llm_tensor, const char *> LLM_TENSOR_NAMES = {
{ LLM_TENSOR_INDEXER_PROJ, "blk.%d.indexer.proj" },
{ LLM_TENSOR_INDEXER_ATTN_K, "blk.%d.indexer.attn_k" },
{ LLM_TENSOR_INDEXER_ATTN_Q_B, "blk.%d.indexer.attn_q_b" },
{ LLM_TENSOR_MASKED_EMBD_CENTROIDS, "masked_embd_centroids" },
{ LLM_TENSOR_MASKED_EMBD_ORDERING, "masked_embd_ordering" },
};
// declare information about the model weight tensors:
@@ -783,6 +785,8 @@ static const std::map<llm_tensor, llm_tensor_info> LLM_TENSOR_INFOS = {
// latent projections feed ggml_mul_mat, the buft probe must use MUL_MAT to keep them on GPU
{LLM_TENSOR_FFN_LATENT_DOWN, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
{LLM_TENSOR_FFN_LATENT_UP, {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL_MAT}},
{LLM_TENSOR_MASKED_EMBD_CENTROIDS, {LLM_TENSOR_LAYER_INPUT, GGML_OP_NONE}},
{LLM_TENSOR_MASKED_EMBD_ORDERING, {LLM_TENSOR_LAYER_INPUT, GGML_OP_NONE}},
};
LLM_KV::LLM_KV(llm_arch arch, const char * suffix) : arch(arch), suffix(suffix) {}
src/llama-arch.h
+3
View File
@@ -566,8 +566,11 @@ enum llm_tensor {
LLM_TENSOR_NEXTN_HNORM,
LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD,
LLM_TENSOR_NEXTN_SHARED_HEAD_NORM,
LLM_TENSOR_MASKED_EMBD_CENTROIDS,
LLM_TENSOR_MASKED_EMBD_ORDERING,
};
enum llm_tensor_layer {
LLM_TENSOR_LAYER_INPUT,
LLM_TENSOR_LAYER_REPEATING,
src/llama-graph.cpp
+13 -4
View File
@@ -567,7 +567,10 @@ void llm_graph_input_attn_kv_iswa::set_input(const llama_ubatch * ubatch) {
mctx->get_base()->set_input_v_idxs(self_v_idxs, ubatch);
}
mctx->get_base()->set_input_kq_mask(self_kq_mask, ubatch, cparams.causal_attn);
// the kq mask guards on its own buffer: shared cells leave idxs unbacked while the mask stays live
if (self_kq_mask && self_kq_mask->buffer) {
mctx->get_base()->set_input_kq_mask(self_kq_mask, ubatch, cparams.causal_attn);
}
// swa tensors may not be allocated if there are no SWA attention layers
if (self_k_idxs_swa && self_k_idxs_swa->buffer) {
@@ -575,7 +578,9 @@ void llm_graph_input_attn_kv_iswa::set_input(const llama_ubatch * ubatch) {
mctx->get_swa()->set_input_v_idxs(self_v_idxs_swa, ubatch);
}
mctx->get_swa()->set_input_kq_mask(self_kq_mask_swa, ubatch, cparams.causal_attn);
if (self_kq_mask_swa && self_kq_mask_swa->buffer) {
mctx->get_swa()->set_input_kq_mask(self_kq_mask_swa, ubatch, cparams.causal_attn);
}
if (self_k_rot) {
mctx->get_base()->set_input_k_rot(self_k_rot);
@@ -607,7 +612,9 @@ bool llm_graph_input_attn_kv_iswa::can_reuse(const llm_graph_params & params) {
//res &= self_v_idxs->ne[0] == params.ubatch.n_tokens; // TODO: need to move this to the unified cache and check there
}
res &= can_reuse_kq_mask(self_kq_mask, mctx->get_base(), params.ubatch, params.cparams);
if (self_kq_mask && self_kq_mask->buffer) {
res &= can_reuse_kq_mask(self_kq_mask, mctx->get_base(), params.ubatch, params.cparams);
}
// swa tensors may not be allocated if there are no SWA attention layers
if (self_k_idxs_swa && self_k_idxs_swa->buffer) {
@@ -615,7 +622,9 @@ bool llm_graph_input_attn_kv_iswa::can_reuse(const llm_graph_params & params) {
//res &= self_v_idxs_swa->ne[0] == params.ubatch.n_tokens; // TODO: need to move this to the unified cache and check there
}
res &= can_reuse_kq_mask(self_kq_mask_swa, mctx->get_swa(), params.ubatch, params.cparams);
if (self_kq_mask_swa && self_kq_mask_swa->buffer) {
res &= can_reuse_kq_mask(self_kq_mask_swa, mctx->get_swa(), params.ubatch, params.cparams);
}
return res;
}
src/models/gemma4-assistant.cpp
+3
View File
@@ -39,6 +39,9 @@ void llama_model_gemma4_assistant::load_arch_tensors(llama_model_loader &) {
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), { n_embd }, 0);
create_tensor(tn(LLM_TENSOR_MASKED_EMBD_CENTROIDS, "weight"), {}, TENSOR_NOT_REQUIRED);
create_tensor(tn(LLM_TENSOR_MASKED_EMBD_ORDERING), {}, TENSOR_NOT_REQUIRED);
const int64_t n_embd_backbone = hparams.n_embd_inp();
nextn_proj_post = create_tensor(tn(LLM_TENSOR_NEXTN_PROJ_POST, "weight"), { n_embd, n_embd_backbone }, 0);
src/models/plamo2.cpp
+5 -1
View File
@@ -11,6 +11,10 @@ void llama_model_plamo2::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);
// Load attention parameters
ml.get_key(LLM_KV_ATTENTION_KEY_LENGTH, hparams.n_embd_head_k_full, false);
ml.get_key(LLM_KV_ATTENTION_VALUE_LENGTH, hparams.n_embd_head_v_full, false);
for (uint32_t i = 0; i < hparams.n_layer(); ++i) {
hparams.is_recr_impl[i] = hparams.n_head_kv(i) == 0;
}
@@ -273,7 +277,7 @@ ggml_tensor * llama_model_plamo2::graph::build_plamo2_mamba_layer(llm_graph_inpu
GGML_ASSERT(n_seqs != 0);
GGML_ASSERT(ubatch.equal_seqs());
GGML_ASSERT(ubatch.n_tokens == n_seq_tokens * n_seqs);
GGML_ASSERT(d_inner % n_head == 0);
GGML_ASSERT(d_inner % n_heads == 0);
GGML_ASSERT(n_group == 0);
ggml_tensor * conv_states_all = mctx_cur->get_r_l(il);