flashinfer: switch to plan API #2904
Merged
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
Narsil
reviewed
Jan 15, 2025
| @@ -235,7 +235,6 @@ def attention( | |||
| paged_kv_cache=(kv_cache.key, kv_cache.value), | |||
| logits_soft_cap=softcap, | |||
| sm_scale=softmax_scale, | |||
| window_left=window_size_left, | |||
There was a problem hiding this comment.
It is already set by the context manager:
This is one of the arguments that is gone in the new run() API.
Narsil
approved these changes
Jan 17, 2025
This change doesn't switch `forward` to `run` yet, since it requires that we have access to the softmax scale and the logit softcap outside the model.
Narsil
force-pushed
the
maintenance/flashinfer-plan
branch
from
a0a0316 to
0ce2dff
Compare
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Outdated suggestions cannot be applied.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.
What does this PR do?
This change switches from the deprecated
begin_forward/end_forwardtoplan.This change doesn't switch
forwardtorunyet, since it requires that we have access to the softmax scale and the logit softcap outside the model.Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.