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

Support DP MLA (#1970)

Browse Source
This commit is contained in:
Ke Bao
2024-11-16 17:01:43 +08:00
committed by GitHub
parent 2f2e07439c
commit 976bc302e5
12 changed files with 395 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.github/workflows/pr-test.yml vendored
View File

@@ -244,6 +244,7 @@ jobs:
cd test/srt
python3 test_mla.py
python3 test_mla_fp8.py
python3 test_dp_attention.py
- name: Evaluate data parallelism accuracy (DP=2)
timeout-minutes: 10