Skip to content

metal : minor fixup in FA kernel #10143

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

Merged
merged 3 commits into from
Nov 3, 2024
Merged

metal : minor fixup in FA kernel #10143

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
40e7172
metal : minor fixup in FA kernel
ggerganov Nov 2, 2024
fd7d5e8
metal : use the unrolled loop variable
ggerganov Nov 3, 2024
909cfd4
metal : remove unused var
ggerganov Nov 3, 2024
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: 3 additions & 3 deletions ggml/src/ggml-metal.metal
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2776,11 +2776,11 @@ kernel void kernel_flash_attn_ext_vec_f16(
const short iv3 = iq3 / rv3;

// load the queries from shared memory into local memory
float4 mq[D4];
float4 mq[D4/NW];

for (short ii = 0; ii < D4; ii += NW) {
short i = ii + tiisg;
mq[i] = (float4) sq4[i];
mq[i/NW] = (float4) sq4[i];
}

// pointer to the mask
Expand Down Expand Up @@ -2812,7 +2812,7 @@ kernel void kernel_flash_attn_ext_vec_f16(
mk[2] = (float4) pk4[i + 2*(nb11/8)];
mk[3] = (float4) pk4[i + 3*(nb11/8)];

mqk += (float4) (mq[i] * mk);
mqk += (float4) (mq[i/NW] * mk);
}

// reduce the results from the threads in the simdgroup
Expand Down
Loading