[Unity][Contrib] Add vLLM paged attention kernel - #16350
Merged
Merged
Conversation
masahi
approved these changes
Jan 5, 2024
vinx13
added a commit
to vinx13/tvm
that referenced
this pull request
Jan 6, 2024
* Add vllm kernels * Add vllm paged attention v2 * [vllm] remove head_mapping * revert cmake changes * add kernel for copying cache blocks * add kernel for reconstructing past kv tensors from cache * lint --------- Co-authored-by: Masahiro Masuda <masahi129@gmail.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 adds vLLM paged attention v1/v2 and cache update kernels as contrib. This can be used by MLC to enable batched inference, see mlc-ai/mlc-llm#1134.
Supersedes #15995
@tqchen @MasterJH5574 @yzh119 @yelite @sunggg @masahi