Use more parallelism in the QKV projections of the MHA block.#176
Merged
copybara-service[bot] merged 1 commit intogoogle:devfrom May 2, 2024
Merged
Use more parallelism in the QKV projections of the MHA block.#176copybara-service[bot] merged 1 commit intogoogle:devfrom
copybara-service[bot] merged 1 commit intogoogle:devfrom
Conversation
We compute all three projections with one MatVec and then copy
the kv part to the cache.
Benchmark results for 7b-it model that uses MHA blocks (summarization with
1600 tokens for prefill and essay writing with 500 tokens for generation):
```
Prefill speed Generation speed
Num threads BEFORE AFTER BEFORE AFTER
32 13.75 t/s 14.80 t/s 9.22 t/s 9.77 t/s
64 19.89 t/s 24.83 t/s 12.46 t/s 13.66 t/s
```
Member
jan-wassenberg
left a comment
jan-wassenberg
left a comment
There was a problem hiding this comment.
Great to get rid of MatVecLoop! Just to confirm that the MQA 2B still works?
Collaborator
Author
Yes, I tested that it still works. |
jan-wassenberg
added
the
copybara-import
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
We compute all three projections with one MatVec and then copy the kv part to the cache.
Benchmark results for 7b-it model that uses MHA blocks (summarization with 1600 tokens for prefill and essay writing with 500 tokens for generation):