xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-07 20:17:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

cleanup flashmla.py

Browse Source 
Signed-off-by: Sage Moore <sage@neuralmagic.com>
This commit is contained in:
Sage Moore 2025-07-03 13:45:52 +00:00
parent 7e2ff2620e
commit 2f3461ad23
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/v1/attention/backends/mla/flashmla.py
View File

@ -76,7 +76,6 @@ class FlashMLAMetadataBuilder(MLACommonMetadataBuilder[FlashMLAMetadata]):
)
if self.runner.full_cuda_graph:
n = num_splits.size(0)
# First time around (CUDAGraph capture), allocate the static buffer
if self.cg_buf_tile_scheduler_metadata is None:
self.cg_buf_tile_scheduler_metadata = tile_scheduler_metadata