Skip to content

[full_graph] Fix query_start_loc padding #19321

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

Merged
merged 1 commit into from
Jun 9, 2025
Merged

[full_graph] Fix query_start_loc padding #19321

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
5 changes: 4 additions & 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 @@ -655,7 +655,10 @@ def _prepare_inputs(

# Fill unused with -1. Needed for reshape_and_cache
self.seq_lens[num_reqs:].fill_(0)
self.query_start_loc[num_reqs + 1:].fill_(-1)
# Note: pad query_start_loc to be non-decreasing, as kernels
# like FlashAttention requires that
self.query_start_loc[num_reqs + 1:].fill_(
self.query_start_loc_cpu[num_reqs].item())
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think .item() will cause 2-way GPU-CPU transfer for a single value, any way we could avoid that?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's a cpu tensor here.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yeah, cpu tensor should be fine.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh my bad - that seems fine then


query_start_loc = self.query_start_loc[:num_reqs + 1]
seq_lens = self.seq_lens[:num_reqs]
Expand Down