tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-30 22:23:31 -04:00
Code Issues Packages Projects Releases Wiki Activity

kompute: add mul_mat_q4_k shader (#10097)

Browse Source 
This is a more or less direct translation from the Metal implementation
to GLSL.

Signed-off-by: Sergio Lopez <slp@redhat.com>
This commit is contained in:
Sergio López
2024-10-31 10:09:52 +01:00
committed by GitHub
parent 61408e7fad
commit 1329c0a75e
4 changed files with 186 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/CMakeLists.txt
View File

@@ -800,6 +800,7 @@ if (GGML_KOMPUTE)
kompute-shaders/op_mul_mat_q8_0.comp
kompute-shaders/op_mul_mat_q4_0.comp
kompute-shaders/op_mul_mat_q4_1.comp
kompute-shaders/op_mul_mat_q4_k.comp
kompute-shaders/op_mul_mat_q6_k.comp
kompute-shaders/op_getrows_f32.comp
kompute-shaders/op_getrows_f16.comp
@@ -833,6 +834,7 @@ if (GGML_KOMPUTE)
shaderop_mul_mat_q8_0.h
shaderop_mul_mat_q4_0.h
shaderop_mul_mat_q4_1.h
shaderop_mul_mat_q4_k.h
shaderop_mul_mat_q6_k.h
shaderop_getrows_f32.h
shaderop_getrows_f16.h