minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Auto Sync] Update detokenizer_manager.py, io_struct.py, mu... (20260120) (#17442)

Browse Source 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Wangfan Fu <wangfan@x.ai>
This commit is contained in:
Lianmin Zheng
2026-01-21 14:48:32 -08:00
committed by GitHub
co-authored by github-actions[bot] Wangfan Fu
parent 95f59c13fd
commit b74a57a8d9
13 changed files with 59 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/quant/test_gptqmodel_dynamic.py
+1 -1
View File
@@ -54,11 +54,11 @@ def check_quant_method(model_path: str, use_marlin_kernel: bool):
model_config=model_config, load_config=load_config, device_config=device_config
)
from sglang.srt.layers.linear import UnquantizedLinearMethod
from sglang.srt.layers.quantization.gptq import (
GPTQLinearMethod,
GPTQMarlinLinearMethod,
)
from sglang.srt.layers.quantization.unquant import UnquantizedLinearMethod
linear_method_cls = (
GPTQMarlinLinearMethod if use_marlin_kernel else (GPTQLinearMethod)