Conversation
Contributor
|
@q10 has exported this pull request. If you are a Meta employee, you can view the originating Diff in D120626878. |
Summary: Restores the ROCm V1 TBE backward launch configuration that was dropped while fixing the host-only CUDA build: `max_segment_length_per_warp` returns to 16384, and `BT_block_size` follows the active GPU warp size. Moves `kWarpSize` and `kWarpSizeHost()` from `cuda_prelude.cuh` into the host-safe `utils/warp_size.h`, so generated host sources can use the runtime query without including device intrinsics. Marks the internal-linkage `kWarpSize` declarations `[[maybe_unused]]` because GCC diagnoses them in generated host translation units where only `kWarpSizeHost()` is used. Defers the ROCm runtime query until `dev_weights` is on GPU. CPU dispatches retain the prior fallback of 64 and do not initialize the HIP runtime. This follows up D119363782 and pytorch#6278, corresponding to pytorch#6323. Reviewed By: gchalump Differential Revision: D120626878
meta-codesync
Bot
changed the title
q10
force-pushed
the
export-D120626878
branch
from
September 18, 2026 18:52
9a02faf to
40af862
Compare
Contributor
|
This pull request has been merged in 659e41f. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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:
Restores the ROCm V1 TBE backward launch configuration that was dropped while fixing the host-only CUDA build:
max_segment_length_per_warpreturns to 16384, andBT_block_sizefollows the active GPU warp size.Moves
kWarpSizeandkWarpSizeHost()fromcuda_prelude.cuhinto the host-safeutils/warp_size.h, so generated host sources can use the runtime query without including device intrinsics.Marks the internal-linkage
kWarpSizedeclarations[[maybe_unused]]because GCC diagnoses them in generated host translation units where onlykWarpSizeHost()is used.Defers the ROCm runtime query until
dev_weightsis on GPU. CPU dispatches retain the prior fallback of 64 and do not initialize the HIP runtime.This follows up D119363782 and #6278, corresponding to #6323.
Reviewed By: gchalump
Differential Revision: D120626878