root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 03:44:35 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

metal : enable mat-vec kernels for bs <= 4

Browse Source
This commit is contained in:
Georgi Gerganov 2024-11-25 10:36:48 +02:00
parent d9d54e498d
commit b1eaad6a91
No known key found for this signature in database
GPG Key ID: BF970631944C16B7
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-metal/ggml-metal.m
View File

@ -1927,7 +1927,7 @@ static void ggml_metal_encode_node(
// 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 = 4;
#if 0
// the numbers below are measured on M2 Ultra for 7B and 13B models