Skip to content

[Bugfix] Fix assertion error in flashmla backend with fullgraph enabled #33496

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Kurumi5210 wants to merge 1 commit into
base: main
Choose a base branch
from
+1 −1
Open

[Bugfix] Fix assertion error in flashmla backend with fullgraph enabled #33496

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion vllm/v1/worker/gpu_model_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4766,7 +4766,7 @@ def _dummy_run(

pad_attn = cudagraph_runtime_mode == CUDAGraphMode.FULL
attn_metadata, _ = self._build_attention_metadata(
num_tokens=num_tokens_unpadded,
num_tokens=num_tokens_padded if pad_attn else num_tokens_unpadded,
num_reqs=num_reqs_padded,
max_query_len=max_query_len,
ubatch_slices=ubatch_slices_padded if pad_attn else ubatch_slices,
Expand Down
Loading