Skip to content

Commit

Permalink
metal : try to improve batched decoding
Browse files Browse the repository at this point in the history
  • Loading branch information
ggerganov committed Dec 1, 2023
1 parent 3e68df8 commit 3cb1c34
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion ggml-metal.m
Original file line number Diff line number Diff line change
Expand Up @@ -1083,7 +1083,7 @@ void ggml_metal_graph_compute(

// find the break-even point where the matrix-matrix kernel becomes more efficient compared
// to the matrix-vector kernel
int ne11_mm_min = 1;
int ne11_mm_min = src0t == GGML_TYPE_F16 ? 1 : 16;

#if 0
// the numbers below are measured on M2 Ultra for 7B and 13B models
Expand Down

0 comments on commit 3cb1c34

Please sign in to comment.