Switch attention backend from flex to cuda #139
Merged
Conversation
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
Switches the flash attention backend parameter from "flex" to "cuda" to improve performance and compatibility with CUDA-enabled hardware acceleration.
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR switches the attention backend from "flex" to "cuda" in the modeling implementation to improve performance and ensure compatibility with CUDA-enabled hardware.
- Changes the backend parameter from "flex" to "cuda" in the flash attention function call
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
| ) | ||
|
|
||
| attention_interface: Callable = flash_dmattn_func_auto(backend="flex") | ||
| attention_interface: Callable = flash_dmattn_func_auto(backend="cuda") |
There was a problem hiding this comment.
The flash_dmattn_func_auto function raises an ImportError regardless of the backend parameter, as shown in the context. This change will not have any functional effect since the function always fails. The underlying flash_dmattn dependency needs to be properly installed and the function implementation needs to be updated to actually use the backend parameter.
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Outdated suggestions cannot be applied.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.
Change the attention backend parameter to cuda for improved performance and compatibility with CUDA-enabled hardware.