[Bugfix] Massage MLA's usage of flash attn for RoCM #13310
Merged
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Outdated suggestions cannot be applied.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 PR massages some
vllm_flash_attn
vsflash_attn
interface differences that appeared between a couple of PRs:#12662 added a this fallback to
flash_attn
in order to support MLA on RoCM:vllm/vllm/attention/backends/mla/utils.py
Lines 33 to 36 in 5e5c8e0
Subsequently #12807 updated to use the
vllm_flash_attn
specific arguments that control whether we use FA2 or FA3.