Skip to content

Allow configuring streaming chunk timeout - #221

Draft
jtechapps wants to merge 1 commit into
vllm-project:mainfrom
jtechapps:configurechunksize
Draft

Allow configuring streaming chunk timeout#221
jtechapps wants to merge 1 commit into
vllm-project:mainfrom
jtechapps:configurechunksize

Conversation

@jtechapps

Copy link
Copy Markdown

Summary

Added support for STREAMING_CHUNK_TIMEOUT_S env variable that configures the timeout for chunks during streaming.

Increased the fallback default from 30 seconds to 600 seconds (10 minutes)

Fixes: #220

Test Plan

So far I tested e2e using forked aiperf.

Added support for STREAMING_CHUNK_TIMEOUT_S env variable that configures
the timeout for chunks during streaming.

Increased the fallback default from 30 seconds to 600 seconds (10 minutes)

Signed-off-by: Jacob Murry <jacobmurry@google.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Allow configuring streaming chunk timeout

1 participant