✨ allow single-shard paged attention #86
Open
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
Signed-off-by: Joe Runde <[email protected]>
Not 100% sure but I think we do actually want |
tdoublep
reviewed
May 8, 2024
| @@ -52,6 +53,11 @@ def __init__( | |||
| raise NotImplementedError( | |||
| f"Flash attention currently only supported by the following model types: {NONTP_FLASH_TYPES}" | |||
| ) | |||
| elif PAGED_ATTENTION: | |||
There was a problem hiding this comment.
I think right now we require both PAGED_ATTENTION and FLASH_ATTENTION to be set, so not sure if this should be elif.
|
@tdoublep ah, I was assuming that they were mutually exclusive, if they both need to be set then let me know if you find out why! |
Xaenalt
pushed a commit
to Xaenalt/text-generation-inference
that referenced
this pull request
Sep 16, 2024
Sync release to main branches for 2.11
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Outdated suggestions cannot be applied.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.
This is a small little change to allow llama and bigcode models to work with paged attention on a single shard. Currently if
FLASH_ATTENTIONis not alos set, it will raise