Use more parallelism in attention block in prefill mode.#177
Merged
copybara-service[bot] merged 3 commits intogoogle:devfrom May 3, 2024
Merged
Use more parallelism in attention block in prefill mode.#177copybara-service[bot] merged 3 commits intogoogle:devfrom
copybara-service[bot] merged 3 commits intogoogle:devfrom
Conversation
Move the loop over the tokens inside the attention block and
then create kHeads * num_tokens threads.
This helps the multi-threaded speed only in case of the 2b gemma
model, but to be consistent we move the loop over the tokens inside
the griffin recurrent layer and the FFW layer as well. This is
also a preparation for using the MatMul operation later.
Benchmark results (summarization with 1600 tokens for prefill
and essay writing with 500 tokens for generation):
```
Prefill speed
Num threads BEFORE AFTER
32 61.76 t/s 65.08 t/s
64 89.46 t/s 98.62 t/s
```
jan-wassenberg
requested changes
May 3, 2024
Member
jan-wassenberg
left a comment
jan-wassenberg
left a comment
There was a problem hiding this comment.
Nice, loop + MatVec is starting to look a lot like a matmul!
One small fix and a question:
jan-wassenberg
approved these changes
May 3, 2024
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Move the loop over the tokens inside the attention block and then create kHeads * num_tokens threads.
This helps the multi-threaded speed only in case of the 2b gemma model, but to be consistent we move the loop over the tokens inside the griffin recurrent layer and the FFW layer as well. This is also a preparation for using the MatMul operation later.
Benchmark results (summarization with 1600 tokens for prefill and essay writing with 500 tokens for generation):