Skip to content
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

Jump to bottom

[Misc] Fix minor typo in scheduler #8765

Merged
merged 1 commit into from
Sep 25, 2024
Merged

[Misc] Fix minor typo in scheduler #8765

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
6 changes: 3 additions & 3 deletions vllm/core/scheduler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1477,14 +1477,14 @@ def _get_num_new_tokens(self, seq_group: SequenceGroup,
# the number of new tokens that is dividable by the block size
# to avoid partial block matching.
block_size = self.cache_config.block_size
reminder = budget.token_budget % block_size
if reminder != 0:
remainder = budget.token_budget % block_size
if remainder != 0:
raise ValueError("When enabling chunked prefill and "
"prefix caching, max_num_batched_tokens "
"(chunk size) must be dividable by "
"block size, but got chunk_size "
f"({budget.token_budget}) % block_size "
f"({block_size}) = {reminder}")
f"({block_size}) = {remainder}")
if remaining_token_budget < num_new_tokens:
num_new_tokens = (remaining_token_budget //
block_size) * block_size
Expand Down
Loading