Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-08 13:59:12 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/cann.Dockerfile
#	.devops/cpu.Dockerfile
#	.devops/llama-cli-cann.Dockerfile
#	.devops/nix/package.nix
#	.github/workflows/build-android.yml
#	.github/workflows/build-cann.yml
#	.github/workflows/build-msys.yml
#	.github/workflows/docker.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/gguf-publish.yml
#	.github/workflows/python-lint.yml
#	.github/workflows/release.yml
#	CMakeLists.txt
#	docs/backend/CANN.md
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	scripts/sync_vendor.py
#	tests/test-chat-auto-parser.cpp
#	tests/test-chat.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tests/test-reasoning-budget.cpp
#	tools/cli/cli.cpp
#	tools/server/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo
2026-03-30 20:45:38 +08:00
parent 923d5fc5d0 e397d3885c
commit 42ad89cd86
74 changed files with 2403 additions and 331 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-quant.cpp
+4 -1
View File
@@ -345,9 +345,12 @@ static bool tensor_allows_quantization(const llama_model_quantize_params * param
// do not quantize specific multimodal tensors
quantize &= name.find(".position_embd") == std::string::npos;
quantize &= name.find("sam.patch_embd") == std::string::npos;
quantize &= name.find("sam.pos_embd") == std::string::npos;
quantize &= name.find("sam.neck.") == std::string::npos;
quantize &= name.find("sam.net_") == std::string::npos;
quantize &= name.find(".rel_pos") == std::string::npos;
quantize &= name.find(".patch_embd") == std::string::npos;
quantize &= name.find(".patch_merger") == std::string::npos;
return quantize;
}