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

feat: support flashinfer mla attention for deepseek v3 (#3550)

Browse Source
This commit is contained in:
Yineng Zhang
2025-02-14 08:50:14 +08:00
committed by GitHub
parent 368de3661e
commit 70f894b810
12 changed files with 299 additions and 135 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -317,7 +317,7 @@ def _set_envs_and_config(server_args: ServerArgs):
if server_args.attention_backend == "flashinfer":
assert_pkg_version(
"flashinfer_python",
"0.2.0.post2",
"0.2.1.post1",
"Please uninstall the old version and "
"reinstall the latest version by following the instructions "
"at https://docs.flashinfer.ai/installation.html.",