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-device.m
+2
View File
@@ -1184,6 +1184,7 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te
case GGML_TYPE_F16:
case GGML_TYPE_BF16:
case GGML_TYPE_Q8_0:
case GGML_TYPE_Q1_0:
case GGML_TYPE_Q4_0:
case GGML_TYPE_Q4_1:
case GGML_TYPE_Q5_0:
@@ -1210,6 +1211,7 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te
default:
return false;
}
case GGML_TYPE_Q1_0:
case GGML_TYPE_Q4_0:
case GGML_TYPE_Q4_1:
case GGML_TYPE_Q5_0: