Merge commit '2cd20b72ed3565ac6935911ca0d9b5d73ae70d0d' into concedo_experimental

# Conflicts:
#	CONTRIBUTING.md
#	docs/backend/CANN.md
#	docs/backend/SYCL.md
#	docs/backend/snapdragon/README.md
#	docs/backend/snapdragon/windows.md
#	docs/build.md
#	docs/multimodal/MobileVLM.md
#	docs/ops.md
#	docs/ops/WebGPU.csv
#	examples/debug/README.md
#	examples/llama.vim
#	examples/model-conversion/README.md
#	examples/sycl/README.md
#	ggml/src/ggml-cpu/amx/mmq.cpp
#	ggml/src/ggml-cpu/arch/x86/repack.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-drv.cpp
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hvx-base.h
#	ggml/src/ggml-hexagon/htp/hvx-copy.h
#	ggml/src/ggml-hexagon/htp/hvx-inverse.h
#	ggml/src/ggml-hexagon/htp/hvx-reduce.h
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	ggml/src/ggml-hexagon/htp/worker-pool.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cpy.cl
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/quants.hpp
#	ggml/src/ggml-sycl/softmax.cpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	scripts/pr2wt.sh
#	scripts/server-bench.py
#	scripts/snapdragon/windows/run-cli.ps1
#	tests/test-alloc.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tools/cli/cli.cpp
#	tools/completion/README.md
#	tools/cvector-generator/cvector-generator.cpp
#	tools/imatrix/README.md
#	tools/perplexity/README.md
#	tools/server/public_simplechat/readme.md
#	tools/server/tests/README.md
This commit is contained in:
Concedo
2026-03-10 22:11:08 +08:00
107 changed files with 1037 additions and 314 deletions
+10 -4
View File
@@ -175,6 +175,7 @@ const char * llm_type_name(llm_type type) {
case LLM_TYPE_0_3B: return "0.3B";
case LLM_TYPE_0_5B: return "0.5B";
case LLM_TYPE_0_6B: return "0.6B";
case LLM_TYPE_0_8B: return "0.8B";
case LLM_TYPE_1B: return "1B";
case LLM_TYPE_1_2B: return "1.2B";
case LLM_TYPE_1_3B: return "1.3B";
@@ -246,12 +247,14 @@ const char * llm_type_name(llm_type type) {
case LLM_TYPE_100B_A6B: return "100B.A6B";
case LLM_TYPE_102B_A12B: return "102B.A12B";
case LLM_TYPE_106B_A12B: return "106B.A12B";
case LLM_TYPE_122B_A10B: return "122B.A10B";
case LLM_TYPE_196B_A11B: return "196B.A11B";
case LLM_TYPE_230B_A10B: return "230B.A10B";
case LLM_TYPE_235B_A22B: return "235B.A22B";
case LLM_TYPE_300B_A47B: return "300B.A47B";
case LLM_TYPE_310B_A15B: return "310B.A15B";
case LLM_TYPE_355B_A32B: return "355B.A32B";
case LLM_TYPE_397B_A17B: return "397B.A17B";
case LLM_TYPE_744B_A40B: return "744B.A40B";
case LLM_TYPE_E2B: return "E2B";
case LLM_TYPE_E4B: return "E4B";
@@ -1638,7 +1641,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
}
switch (hparams.n_layer) {
// TODO: Jamba layers are a bit heterogenous, so naming this is hard.
// TODO: Jamba layers are a bit heterogeneous, so naming this is hard.
case 12: // 900M 8x???M
case 32: // 51B 16x?B
default: type = LLM_TYPE_UNKNOWN;
@@ -2642,7 +2645,9 @@ void llama_model::load_hparams(llama_model_loader & ml) {
}
switch (hparams.n_layer) {
case 24: type = LLM_TYPE_2B; break;
case 24: type = hparams.n_embd == 1024 ? LLM_TYPE_0_8B : LLM_TYPE_2B; break;
case 32: type = hparams.n_embd == 2560 ? LLM_TYPE_4B : LLM_TYPE_9B; break;
case 64: type = LLM_TYPE_27B; break;
default: type = LLM_TYPE_UNKNOWN;
}
} break;
@@ -2671,8 +2676,9 @@ void llama_model::load_hparams(llama_model_loader & ml) {
}
switch (hparams.n_layer) {
case 28: type = LLM_TYPE_35B_A3B; break;
case 48: type = LLM_TYPE_80B_A3B; break;
case 40: type = LLM_TYPE_35B_A3B; break;
case 48: type = LLM_TYPE_122B_A10B; break;
case 60: type = LLM_TYPE_397B_A17B; break;
default: type = LLM_TYPE_UNKNOWN;
}
} break;