[Build] Only build 9.0a for scaled_mm and sparse kernels #12339
Merged
+32
−19
Conversation
This file contains 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! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can do one of these:
🚀 |
Signed-off-by: Lucas Wilkinson <[email protected]>
LucasWilkinson
force-pushed
the
lwilkinson/only-build-90a
branch
from
cc3d9c7 to
0b484aa
Compare
tlrmchlsmth
approved these changes
Jan 24, 2025
| set(_CUDA_ARCHS "9.0a") | ||
| endif() | ||
| endif() | ||
|
|
||
| list(SORT SRC_CUDA_ARCHS COMPARE NATURAL ORDER ASCENDING) | ||
|
|
||
| # for each ARCH in CUDA_ARCHS find the highest arch in SRC_CUDA_ARCHS that is | ||
| # less or eqault to ARCH |
tjtanaa
pushed a commit
to EmbeddedLLM/vllm
that referenced
this pull request
Jan 28, 2025
…t#12339) Signed-off-by: Lucas Wilkinson <[email protected]>
rasmith
pushed a commit
to rasmith/vllm
that referenced
this pull request
Jan 30, 2025
…t#12339) Signed-off-by: Lucas Wilkinson <[email protected]>
Isotr0py
pushed a commit
to Isotr0py/vllm
that referenced
this pull request
Feb 2, 2025
…t#12339) Signed-off-by: Lucas Wilkinson <[email protected]> Signed-off-by: Isotr0py <[email protected]>
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Outdated suggestions cannot be applied.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.
Only build 9.0a for scaled_mm and sparse CUTLASS kernels to save on build time and binary size (instead of 9.0 AND 9.0a). Since these kernels use 9.0a specific features and theres no pure 9.0 systems that we are aware of, only the 9.0a versions are getting used.
Also clean-up the cmake utility fixing a bug where
cuda_archs_loose_intersectionwas ignoring theTGT_CUDA_ARCHSparameter and just usingCUDA_ARCHSdirectlyWheel size:
this PR - 191.42 MB
main - 191.46 MB