8000 [FFPA] fix some macro typos by DefTruth · Pull Request #21 · xlite-dev/ffpa-attn · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

[FFPA] fix some macro typos #21

New issu 8000 e

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

Merged
merged 2 commits into from
Jan 9, 2025
Merged

[FFPA] fix some macro typos #21

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0016726
Update faster_prefill_attn_F16F16F16F16_L1.cu
DefTruth Jan 9, 2025
a02f064
Update faster_prefill_attn_F32F16F16F32_L1.cu
DefTruth Jan 9, 2025
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
4 changes: 2 additions & 2 deletions csrc/cuffpa/faster_prefill_attn_F16F16F16F16_L1.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -450,7 +450,7 @@ void ffpa_mma_acc_f16_L1(torch::Tensor Q,
}

#else
#ifdef ENBALE_FFPA_ALL_HEADDIM
#ifdef ENABLE_FFPA_ALL_HEADDIM
// multiple of 32
#define DISPATCH_KERNEL_F16_L1_HEADDIM(S) \
{ \
Expand Down Expand Up @@ -523,7 +523,7 @@ void ffpa_mma_acc_f16_L1(torch::Tensor Q,

#endif

#ifdef ENBALE_FFPA_ALL_STAGES
#ifdef ENABLE_FFPA_ALL_STAGES
// dispatch stages
if (stages == 2) {
DISPATCH_KERNEL_F16_L1_HEADDIM(2);
Expand Down
4 changes: 2 additions & 2 deletions csrc/cuffpa/faster_prefill_attn_F32F16F16F32_L1.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -452,7 +452,7 @@ void ffpa_mma_acc_f32_L1(torch::Tensor Q,
}

#else
#ifdef ENBALE_FFPA_ALL_HEADDIM
#ifdef ENABLE_FFPA_ALL_HEADDIM
// multiple of 32
#define DISPATCH_KERNEL_F32_L1_HEADDIM(S) \
{ \
Expand Down Expand Up @@ -525,7 +525,7 @@ void ffpa_mma_acc_f32_L1(torch::Tensor Q,

#endif

#ifdef ENBALE_FFPA_ALL_STAGES
#ifdef ENABLE_FFPA_ALL_STAGES
// dispatch stages
if (stages == 2) {
DISPATCH_KERNEL_F32_L1_HEADDIM(2);
Expand Down
0