Add opt-in MI350 pack_segments fused kernel - #6263
Open
Ruishenl wants to merge 1 commit into
Open
Conversation
Summary:
Add an opt-in fused prefix-and-pack kernel for gfx950 inputs with at most 128 segments. `FBGEMM_ENABLE_PACK_SEGMENTS_SMALL_N=1` removes the separate exclusive-cumsum launch while preserving the legacy `CUDA_KERNEL_ASSERT` input invariant. The path remains disabled by default pending broader workload validation.
{F1995545397}
Differential Revision: D118393046
meta-codesync
Bot
changed the title
Ruishenl
force-pushed
the
export-D118393046
branch
from
September 2, 2026 21:07
cddd3af to
dcb229c
Compare
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary:
Add an opt-in fused prefix-and-pack kernel for gfx950 inputs with at most 128 segments.
FBGEMM_ENABLE_PACK_SEGMENTS_SMALL_N=1removes the separate exclusive-cumsum launch while preserving the legacyCUDA_KERNEL_ASSERTinput invariant. The path remains disabled by default pending broader workload validation.{F1995545397}
Differential Revision: D118393046