Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-10 06:49:12 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-webgpu.yml
#	CMakeLists.txt
#	common/CMakeLists.txt
#	docs/development/HOWTO-add-model.md
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/CMakeLists.txt
#	tests/test-arg-parser.cpp
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
#	tests/test-save-load-state.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo
2026-07-27 22:28:38 +08:00
parent 90510f2b27 0324696b8e
commit fee0bf446c
74 changed files with 2516 additions and 361 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+6 -1
View File
@@ -121,6 +121,7 @@
#include "models/minicpm.cpp"
#include "models/minicpm3.cpp"
#include "models/minimax-m2.cpp"
#include "models/minimax-m3.cpp"
#include "models/mistral3.cpp"
#include "models/mistral4.cpp"
#include "models/modern-bert.cpp"
@@ -425,6 +426,8 @@ static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params
return new llama_model_apertus(params);
case LLM_ARCH_MINIMAX_M2:
return new llama_model_minimax_m2(params);
case LLM_ARCH_MINIMAX_M3:
return new llama_model_minimax_m3(params);
case LLM_ARCH_COGVLM:
return new llama_model_cogvlm(params);
case LLM_ARCH_PANGU_EMBED:
@@ -958,6 +961,7 @@ const char * llm_type_name(llm_type type) {
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_428B_A23B: return "428B.A23B";
case LLM_TYPE_235B_A22B: return "235B.A22B";
case LLM_TYPE_300B_A47B: return "300B.A47B";
case LLM_TYPE_310B_A15B: return "310B.A15B";
@@ -1386,7 +1390,7 @@ void llama_model_base::load_vocab(llama_model_loader & ml) {
bool llama_model_base::load_tensors(llama_model_loader & ml) {
const auto & split_mode = params.split_mode;
const bool use_mlock = params.load_mode == LLAMA_LOAD_MODE_MLOCK;
const bool use_mlock = params.load_mode == LLAMA_LOAD_MODE_MLOCK || params.load_mode == LLAMA_LOAD_MODE_MMAP_MLOCK;
const auto & tensor_split = params.tensor_split;
const int n_layer_all = hparams.n_layer_all;
@@ -2690,6 +2694,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
case LLM_ARCH_GROVEMOE:
case LLM_ARCH_APERTUS:
case LLM_ARCH_MINIMAX_M2:
case LLM_ARCH_MINIMAX_M3:
case LLM_ARCH_COGVLM:
case LLM_ARCH_PANGU_EMBED:
case LLM_ARCH_AFMOE: