Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

metal: Q1_0 backend (#21528)

Browse Source 
* initial Q1_0 Metal backend

* tuning q1_0 metal kernels

* add Q1_0 to test-backend-ops

* add Q1_0<->F32 copy test

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Pasha Khosravi
2026-04-08 16:07:47 +03:00
committed by GitHub
co-authored by Georgi Gerganov
parent 5764d7c6a6
commit dcdcbad42a
6 changed files with 205 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-ops.cpp
+1
View File
@@ -2047,6 +2047,7 @@ int ggml_metal_op_mul_mat(ggml_metal_op_t ctx, int idx) {
op->src[0]->type == GGML_TYPE_F32 || // TODO: helper function
op->src[0]->type == GGML_TYPE_F16 ||
op->src[0]->type == GGML_TYPE_BF16 ||
op->src[0]->type == GGML_TYPE_Q1_0 ||
op->src[0]->type == GGML_TYPE_Q4_0 ||
op->src[0]->type == GGML_TYPE_Q4_1 ||
op->src[0]->type == GGML_TYPE_Q5_0 ||