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

Fix fast decode plan for flashinfer v0.4.0rc1 and upgrade sgl-kernel 0.3.11 (#10634)

Browse Source 
Co-authored-by: zhyncs <me@zhyncs.com>
This commit is contained in:
Baizhou Zhang
2025-09-19 01:25:29 -07:00
committed by GitHub
parent 4f2055ad56
commit 3fa3c22ae2
5 changed files with 10 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
python/sglang/srt/entrypoints/engine.py
View File

@@ -703,7 +703,7 @@ def _set_envs_and_config(server_args: ServerArgs):
if server_args.attention_backend == "flashinfer":
assert_pkg_version(
"flashinfer_python",
"0.3.1",
"0.4.0rc1",
"Please uninstall the old version and "
"reinstall the latest version by following the instructions "
"at https://docs.flashinfer.ai/installation.html.",
@@ -711,7 +711,7 @@ 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",
"0.3.10",
"0.3.11",
"Please reinstall the latest version with `pip install sgl-kernel --force-reinstall`",
)