Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-06 13:01:21 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '0fac87b157305eb82a70902327abffbbce25bd3e' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build-android.yml
#	.github/workflows/hip-quality-check.yml
#	docs/multimodal.md
#	scripts/hip/gcn-cdna-vgpr-check.py
#	scripts/snapdragon/windows/run-bench.ps1
#	scripts/snapdragon/windows/run-cli.ps1
#	scripts/snapdragon/windows/run-tool.ps1
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
#	tools/imatrix/imatrix.cpp
#	tools/mtmd/CMakeLists.txt
This commit is contained in:
Concedo
2026-03-29 01:14:33 +08:00
parent 674b7f5eee 0fac87b157
commit aac220f7e3
32 changed files with 1371 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-quant.cpp
+4 -1
View File
@@ -344,7 +344,10 @@ static bool tensor_allows_quantization(const llama_model_quantize_params * param
quantize &= name.find("attn_rel_b.weight") == std::string::npos;
// do not quantize specific multimodal tensors
quantize &= name.find(".position_embd.") == std::string::npos;
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(".rel_pos") == std::string::npos;
return quantize;
}