biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix][CI] fix typos (#34934)

Browse Source 
Signed-off-by: 1195343015 <1195343015@qq.com>
Signed-off-by: Jiayi Yan <66017932+1195343015@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Jiayi Yan
2026-03-06 01:05:46 +08:00
committed by GitHub
parent 8c760b6ab6
commit 6a895197fa
98 changed files with 227 additions and 366 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/attention/mla_attention.py
View File

@@ -2540,7 +2540,7 @@ class MLACommonImpl(MLAAttentionImpl[M], Generic[M]):
)
# workspace
# |------- N tokens --------|--------- N*dcp_size tokens ----------|
# |<- use for loca_gather ->|<--------- use for allgather -------->|
# |<- use for local_gather ->|<--------- use for allgather -------->|
allgather_offset = workspace.shape[0] // (dcp_world_size + 1)
assert allgather_offset * (dcp_world_size + 1) == workspace.shape[0]
assert toks <= allgather_offset