Allow overwrite flashinfer use_tensorcore #2169
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
merrymercy
requested review from
Ying1123,
hnyls2002,
zhyncs,
ispobock and
ByronHsu
as code owners
zhyncs
reviewed
Nov 25, 2024
| else: | ||
| self.decode_use_tensor_cores = False | ||
| if not _grouped_size_compiled_for_decode_kernels( |
There was a problem hiding this comment.
May we remove this _grouped_size_compiled_for_decode_kernels I think it's useless in FlashInfer v0.2 cc @yzh119
There was a problem hiding this comment.
Yes we can use some heuristic:
- For fp16,
use_tensor_cores=Truewhen gqa_group_size > 4 - For fp8, we can always enable
use_tensor_cores=True
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Outdated suggestions cannot be applied.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.
No description provided.