Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-01 10:00:51 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	tools/ui/src/lib/constants/settings-registry.ts
This commit is contained in:
Concedo
2026-07-21 20:28:51 +08:00
parent 601e13b507 76f46ad29d
commit ee517d0d1b
38 changed files with 1638 additions and 471 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-quant.cpp
+3
View File
@@ -306,6 +306,9 @@ static bool tensor_allows_quantization(const llama_model_quantize_params * param
// NOTE: can't use LLM_TN here because the layer number is not known
quantize &= name.find("ffn_gate_inp.weight") == std::string::npos;
// do not quantize the i32 token-id -> expert-id routing table (DeepSeek-V4)
quantize &= name.find("ffn_gate_tid2eid.weight") == std::string::npos;
// these are very small (e.g. 4x4)
quantize &= name.find("altup") == std::string::npos;
quantize &= name.find("laurel") == std::string::npos;