Skip to content

Metal: Fix flash_attn_ext assertion by applying consistent has_kvpad logic #17294

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

Metal: Fix flash_attn_ext assertion by applying consistent has_kvpad logic #17294

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
6 changes: 4 additions & 2 deletions ggml/src/ggml-metal/ggml-metal-ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2153,7 +2153,8 @@ int ggml_metal_op_flash_attn_ext(ggml_metal_op_t ctx, int idx) {

bool need_sync = false;

const bool has_kvpad = ne11 % ncpsg != 0;
// const bool has_kvpad = ne11 % ncpsg != 0;
const bool has_kvpad = true;

if (has_kvpad) {
assert(ggml_metal_op_flash_attn_ext_extra_pad(op) != 0);
Expand Down Expand Up @@ -2325,7 +2326,8 @@ int ggml_metal_op_flash_attn_ext(ggml_metal_op_t ctx, int idx) {

bool need_sync = false;

const bool has_kvpad = ne11 % ncpsg != 0;
// const bool has_kvpad = ne11 % ncpsg != 0;
const bool has_kvpad = true;

if (has_kvpad) {
assert(ggml_metal_op_flash_attn_ext_extra_pad(op) != 0);
Expand Down