Skip to content

fix missing standard headers in group_norm_v2 host template#2010

Open
ZhiyuanChen wants to merge 1 commit into
NVIDIA:masterfrom
ZhiyuanChen:patch-2
Open

fix missing standard headers in group_norm_v2 host template#2010
ZhiyuanChen wants to merge 1 commit into
NVIDIA:masterfrom
ZhiyuanChen:patch-2

Conversation

@ZhiyuanChen
Copy link
Copy Markdown
Contributor

APEX_GROUP_NORM=1 builds group_norm_v2_cuda on CUDA >= 12.4. With CUDA 12.8 / GCC 11, compilation fails in gn_cuda_host_template.cuh because std::tuple/std::get/std::make_tuple are used without including .

This patch adds the standard headers used directly by the file.

APEX_GROUP_NORM=1 builds group_norm_v2_cuda on CUDA >= 12.4.
With CUDA 12.8 / GCC 11, compilation fails in gn_cuda_host_template.cuh because std::tuple/std::get/std::make_tuple are used without including <tuple>.

This patch adds the standard headers used directly by the file.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant