fix(cuda): include cooperative_groups/reduce.h for CUDA 13 (libkernels.so build)#123
Merged
Conversation
CUDA 13 moved cg::reduce / cg::plus out of <cooperative_groups.h> into <cooperative_groups/reduce.h>. Without the explicit include, gemv_q4k_sm121.cu fails to compile (libkernels.so build breaks) under nvcc 13.x. Verified: the sm_121 (GB10) kernel build succeeds with this include added.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
On CUDA 13 (nvcc 13.x),
make sharedfails compilinggemv_q4k_sm121.cu:CUDA 13 moved
cg::reduce/cg::plusout of<cooperative_groups.h>into<cooperative_groups/reduce.h>. The file only included the former, so the wholelibkernels.sobuild breaks on CUDA 13 toolchains (e.g. the GB10 DGX, CUDA 13.0).Fix
Add
#include <cooperative_groups/reduce.h>. Verified:make shared CUDA_ARCH=sm_121builds cleanly on the GB10 DGX (CUDA 13.0) after this change. No behavior change on older CUDA (header is additive).