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

metal : fix mul-mm condition + fix mul-mv permuted kernels (#16494)

Browse Source
This commit is contained in:
Georgi Gerganov
2025-10-11 16:54:10 +03:00
committed by GitHub
parent 4a8fbe0a5e
commit a3cb04744f
3 changed files with 44 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-ops.cpp
+2 -3
View File
@@ -1546,9 +1546,8 @@ int ggml_metal_op_mul_mat(ggml_metal_op_t ctx, int idx) {
!ggml_is_transposed(op->src[1]) &&
// for now the matrix-matrix multiplication kernel only works on A14+/M1+ SoCs
// AMD GPU and older A-chips will reuse matrix-vector multiplication kernel
props_dev->has_simdgroup_mm && ne00 >= 64 &&
(ne11 > ne11_mm_min || (ggml_is_quantized(op->src[0]->type) && ne12 > 1))) {
//printf("matrix: ne00 = %6d, ne01 = %6d, ne02 = %6d, ne11 = %6d, ne12 = %6d\n", ne00, ne01, ne02, ne11, ne12);
props_dev->has_simdgroup_mm && ne00 >= 64 && ne11 > ne11_mm_min) {
//GGML_LOG_INFO("matrix: ne00 = %6d, ne01 = %6d, ne02 = %6d, ne11 = %6d, ne12 = %6d\n", ne00, ne01, ne02, ne11, ne12);
// some Metal matrix data types require aligned pointers
// ref: https://developer.apple.com/metal/Metal-Shading-Language-Specification.pdf (Table 2.5)