EngineX/xc-llm-kunlun
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[dev] support AWQ/GPTQ quantization for dense models

Browse Source
This commit is contained in:
Li Wei
2025-12-24 13:45:55 +08:00
parent 75d0bdae2f
commit 6546323c71
5 changed files with 412 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
requirements.txt
View File

@@ -9,7 +9,7 @@ blake3==1.0.5
cachetools==6.1.0
cbor2==5.7.0
cloudpickle==3.1.1
compressed-tensors==0.10.2
compressed-tensors==0.11.0
diskcache==5.6.3
gguf==0.17.1
mistral_common==1.8.3