chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 14 Packages Projects Releases Wiki Activity

Add AWQ quantization support for NPU. (#10158)

Browse Source 
Co-authored-by: Alisehen <814073252@qq.com>
Co-authored-by: Yaochen Han <48639761+Alisehen@users.noreply.github.com>
Co-authored-by: Zhengda Qin <zhengdqin@gmail.com>
This commit is contained in:
ErvinXie
2025-10-23 12:08:05 -07:00
committed by GitHub
co-authored by Alisehen Yaochen Han Zhengda Qin
parent 28b8a4064d
commit 39c237f02c
7 changed files with 243 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/layers/linear.py
+1
View File
@@ -51,6 +51,7 @@ WEIGHT_LOADER_V2_SUPPORTED = [
"CompressedTensorsLinearMethod",
"AWQMarlinLinearMethod",
"AWQLinearMethod",
"AWQLinearAscendMethod",
"GPTQMarlinLinearMethod",
"Fp8LinearMethod",
"BlockInt8LinearMethod",