Skip to content

Use the optimized block sizes after tuning the kernel. #14329

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
Mar 7, 2025
Merged

Use the optimized block sizes after tuning the kernel. #14329

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
4 changes: 2 additions & 2 deletions vllm/v1/attention/backends/pallas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,8 +12,8 @@
from vllm.attention.backends.utils import CommonAttentionState

# These are the 2 tunable parameters of the paged attention Pallas kernel.
NUM_QUERIES_PER_BLOCK = 32
NUM_KV_PAGES_PER_BLOCK = 128
NUM_QUERIES_PER_BLOCK = 16
NUM_KV_PAGES_PER_BLOCK = 256


class PallasAttentionBackend(AttentionBackend):
Expand Down