Skip to content

feat: enable Metal GEMM for fmt=4 (grouped-int4) weights #591

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
RDouglasSharp wants to merge 1 commit into from
Closed

feat: enable Metal GEMM for fmt=4 (grouped-int4) weights #591

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
2 changes: 1 addition & 1 deletion c/colibri.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -547,7 +547,7 @@ static void matmul_i4_grouped_pair(float *yg, float *yu, const float *x,
* (~+12% perplexity), measured. Every other prefill matmul keeps IDOT as before. */
static void matmul_qt_ex(float *y, const float *x, QT *w, int S, int allow_idot){
#ifdef COLI_METAL
if(g_metal_enabled && S>=g_metal_gemm_min && !spec_pinned() && (w->fmt==1||w->fmt==2) && !omp_in_parallel()){
if(g_metal_enabled && S>=g_metal_gemm_min && !spec_pinned() && (w->fmt==1||w->fmt==2||w->fmt==4) && !omp_in_parallel()){
const void *wp = w->fmt==1 ? (const void*)w->q8 : (const void*)w->q4;
if(coli_metal_gemm(y,x,wp,w->s,w->fmt,S,w->I,w->O)) return;
}
Expand Down
Loading