Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix turbomind build on sm<80 #754

Merged
merged 2 commits into from
Nov 29, 2023
Merged

fix turbomind build on sm<80 #754

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
295715d
fix
grimoire Nov 24, 2023
a81bde3
fix lint
Nov 24, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions src/turbomind/models/llama/flash_attention2/flash_fwd_launch_template.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,13 @@
template<typename Kernel_traits, bool Is_dropout, bool Is_causal, bool Is_even_N, bool Is_even_K, bool Return_softmax>
__global__ void flash_fwd_kernel(Flash_fwd_params params)
{

#if __CUDA_ARCH__ >= 800
flash::compute_attn<Kernel_traits, Is_dropout, Is_causal, Is_even_N, Is_even_K, Return_softmax>(params);
#else
// TODO: support flash attention2 on sm<80
assert(false);
lvhan028 marked this conversation as resolved.
Show resolved Hide resolved
#endif
}

template<typename Kernel_traits, bool Is_dropout, bool Is_causal>
Expand Down
Loading