Add flash attention support for inference #367
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
|
flash-attention and speculative sampling work correctly, but the inference speed is slow when enabling both CFG sampling and speculative sampling. |
airaria
approved these changes
Oct 26, 2023
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Outdated suggestions cannot be applied.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.
Description
Flash-attention released an updates that optimize for inference. This PR adds the adaptation for speeding up inference with flash-attention.
Specifically, this PR includes:
inference_hf.pyandgradio_demo.pyby adding the--flash_attnparameter.padding_maskin flash attention and xformers patches. This parameter was added inLlamaAttention.forwardfunction in transformers v4.34.Related Issue
Add
padding_mask: #326