Skip to content

support --no-enable-chunked-prefill for V1 #19975

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

support --no-enable-chunked-prefill for V1 #19975

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
3 changes: 2 additions & 1 deletion vllm/engine/arg_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1545,7 +1545,8 @@ def _set_default_args_v1(self, usage_context: UsageContext,
# for non-pooling tasks.
# For pooling tasks the default is False
if model_config.runner_type != "pooling":
self.enable_chunked_prefill = True
if self.enable_chunked_prefill is None:
self.enable_chunked_prefill = True
Comment on lines +1548 to +1549
Copy link
Contributor

Choose a reason for hiding this comment

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

medium

This change introduces a check for self.enable_chunked_prefill being None before setting it to True. This is good, but it would be clearer to have a comment explaining why this check is necessary, especially in the context of the --no-enable-chunked-prefill parameter. Consider adding a comment to clarify the purpose of this conditional check.

Suggested change
if self.enable_chunked_prefill is None:
self.enable_chunked_prefill = True
# Only enable chunked prefill if it hasn't been explicitly disabled via --no-enable-chunked-prefill
if self.enable_chunked_prefill is None:
self.enable_chunked_prefill = True

if self.enable_prefix_caching is None:
self.enable_prefix_caching = True
else:
Expand Down