This repository has been archived by the owner on Oct 11, 2024. It is now read-only.
Upstream sync 2024 04 26 #211
Merged
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
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
[Core][Distributed] use existing torch.cuda.device context manager (vllm-project#4318)
This PR addresses the Marlin kernel H100 crash that was reported here: neuralmagic#187. The reason for the crash was the inline PTX assembly that introduced the async_copy with streaming behavior. The solution is to use the more standard PTX for async_copy (without the fractional L2 policy for "evict_first"). There is no performance difference between standard async_copy PTX and the previous one.
Co-authored-by: Simon Mo <simon.mo@hey.com>
…formers 4.40.0 (vllm-project#4324) Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Caio Mendes <caiocesart@microsoft.com>
SageMoore
approved these changes
Apr 30, 2024
mgoin
reviewed
Apr 30, 2024
mgoin
approved these changes
Apr 30, 2024
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Upstream sync 2024 04 26 (#211)
SUMMARY:
Merge commits from vllm-project@a37d815 to vllm-project@b6dcb4d
Note that vllm-project@a37d815 is NOT included in this merge.