update llama flash attention#646
Merged
Merged
Conversation
Collaborator
Author
a40 traindataset:alpacallama2-7b, 2048 blocksize, 10 batchsize, gradient checkpoint a40 evaldataset:MedQA-USMLE validation, block_size:4096, batch size:10accsame acc in first 200 samples:0.41 memory:with flash attention:39752mb |
Collaborator
Author
bugs need to be fixed in the future
|
research4pan
approved these changes
Sep 19, 2023
research4pan
left a comment
Contributor
There was a problem hiding this comment.
LGTM, update llama flash attention implementation to make it compatible with latest version of transformers and flash_attention. Major changes are
- Support
past_key_valuecache optimization of reusing key value tensor caches during token-by-token decoding - Flash attention is not enabled during token-by-token decoding or incremental state decoding
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
1.update llama flash attention code(past_key_value, attention_mask)
2.support flash attention + kv_cache now.