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

[AMD][Quantization] Add int4fp8_moe online quantization on ROCm (#7392)

Browse Source 
Co-authored-by: Dehua Tang <dehtang@amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: YC Tseng <yctseng@amd.com>
This commit is contained in:
fxmarty-amd
2026-01-14 01:44:40 -08:00
committed by GitHub
co-authored by Dehua Tang HAI YC Tseng
parent feae615b11
commit 5af84c8af5
12 changed files with 615 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/layers/linear.py
+1
View File
@@ -66,6 +66,7 @@ WEIGHT_LOADER_V2_SUPPORTED = [
"ModelOptFp4LinearMethod",
"IPEXAWQLinearMethod",
"PetitNvFp4LinearMethod",
"QuarkInt4Fp8LinearMethod",
]
_is_cpu = is_cpu()