Aciddelgado/gqa local #18375
Merged
Aciddelgado/gqa local #18375
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
| attention = attention.masked_fill(torch.all(causal_mask, dim=-1, keepdim=True), 0.0) | ||
| # Some rows might be completely masked out so we fill them with zero instead of NaN | ||
| if window_size[0] >= 0 or window_size[1] >= 0: | ||
| attention = attention.masked_fill(torch.all(local_mask, dim=-1, keepdim=True), 0.0) |
Check failure
Code scanning / CodeQL
Potentially uninitialized local variable
tianleiwu
reviewed
Nov 16, 2023
tianleiwu
reviewed
Nov 16, 2023
yufenglee
approved these changes
Nov 16, 2023
kleiti
pushed a commit
to kleiti/onnxruntime
that referenced
this pull request
Mar 22, 2024
### Description Implement preliminary version of local (sliding window) attention. Currently only supported by Flash Attention (sm >= 80, Linux). Currently only supports sliding attention with a large cached kv. ### Motivation and Context This change enables to run Mistral and other models which use sliding window attention.
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Outdated suggestions cannot be applied.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
Implement preliminary version of local (sliding window) attention. Currently only supported by Flash Attention (sm >= 80, Linux). Currently only supports sliding attention with a large cached kv.
Motivation and Context
This change enables to run Mistral and other models which use sliding window attention.