[build] Avoid building too many extensions #1624
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Hi @ymwangg, sorry for the late review. Could you resolve the merge conflicts before I get into the review? No worries if you can't. We can do it ourselves if you can't. |
ymwangg
force-pushed
the
improve_build
branch
from
98027ec to
fac39fa
Compare
ymwangg
force-pushed
the
improve_build
branch
from
fac39fa to
321610c
Compare
|
@WoosukKwon sure, I've rebased. |
WoosukKwon
approved these changes
Nov 24, 2023
There was a problem hiding this comment.
@ymwangg LGTM. Awesome! The compilation time reduced from 13 mins to 3.5 mins on my machine. Thanks for the PR!
xjpang
pushed a commit
to xjpang/vllm
that referenced
this pull request
Dec 4, 2023
hongxiayang
pushed a commit
to hongxiayang/vllm
that referenced
this pull request
Feb 13, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR lets vllm only build one extension and reduces the build time by 75% (from ~5.5min to ~1.5min) based on my test.