EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[4/n]decouple quantization implementation from vLLM dependency (#9191)

Browse Source 
Co-authored-by: AniZpZ <aniz1905@gmail.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
This commit is contained in:
Hongbo Xu
2025-08-15 03:05:46 +08:00
committed by GitHub
parent 63d82a776a
commit 2cc9eeab01
8 changed files with 37 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/sglang/srt/entrypoints/engine.py
View File

@@ -655,7 +655,7 @@ def _set_envs_and_config(server_args: ServerArgs):
if _is_cuda and not get_bool_env_var("SGLANG_SKIP_SGL_KERNEL_VERSION_CHECK"):
assert_pkg_version(
"sgl-kernel",
"0.3.4",
"0.3.5",
"Please reinstall the latest version with `pip install sgl-kernel --force-reinstall`",
)