Add receipt for pytorch #791
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
alugorey
requested review from
Copilot and
slippedJim
and removed request for
Copilot
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR adds a new receipt variant (receipt 6) for PyTorch that excludes the BATCH_PREFILL API variant, which is currently unsupported by PyTorch.
- Adds receipt 6 that includes only COMBINED_API and FMHA_FWD_SPLITKV_API variants
- Removes FMHA_BATCH_PREFILL_API from the new receipt to accommodate PyTorch limitations
Contributor
Author
|
@pytorchbot merge |
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Outdated suggestions cannot be applied.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.
The current "combined" api receipt includes batch_prefill variant. Pytorch does not support this (yet). Creating a new receipt that removes the BATCH_PREFILL variant for a new receipt
6. This change should not cause any regression as it's a path only hit when the receipt for fwd kernel generation is set to 6. Currently only used by PyTorch.