[feat] support minimum token load balance in dp attention (#7379)

This commit is contained in:
Guanhua Wang
2025-08-03 15:46:47 +08:00
committed by GitHub
parent b0add2da00
commit f7b2853ff8
8 changed files with 271 additions and 6 deletions

View File

@@ -732,6 +732,7 @@ def _launch_subprocesses(
pp_rank,
None,
writer,
None,
),
)