Skip to content

revert the L_k padding, introduced as part of #736 #774

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

Closed
wants to merge 1 commit into from
Closed

revert the L_k padding, introduced as part of #736 #774

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 2 additions & 1 deletion ggml_extend.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -875,9 +875,10 @@ __STATIC_INLINE__ struct ggml_tensor* ggml_nn_attention_ext(struct ggml_context*
d_head == 112 ||
d_head == 128 ||
d_head == 256);
#if 0
#if 1
can_use_flash_attn = can_use_flash_attn && L_k % 256 == 0;
#else
// this causes issues, see https://github.com/leejet/stable-diffusion.cpp/issues/756
if (can_use_flash_attn && L_k % 256 != 0) {
// TODO(Green-Sky): might be worth just padding by default
if (L_k == 77 || L_k == 4208 || L_k == 3952) {
Expand Down
Loading