tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

opencl: mark mul_mat f32f32 as supporting non-contiguous tensors (#13790)

Browse Source
This commit is contained in:
lhez
2025-05-27 12:53:14 -07:00
committed by GitHub
parent bef8176387
commit 1701d4c54f
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-opencl/ggml-opencl.cpp
View File

@ -1877,7 +1877,7 @@ static bool ggml_opencl_supports_op(ggml_backend_dev_t dev, const struct ggml_te
if (op->src[0]->type == GGML_TYPE_F16) {
return true;
} else if (op->src[0]->type == GGML_TYPE_F32) {
return op->src[1]->type == GGML_TYPE_F32 && ggml_is_contiguous(op->src[0]) && ggml_is_contiguous(op->src[1]);
return op->src[1]->type == GGML_TYPE_F32;
} else if (op->src[0]->type == GGML_TYPE_Q4_0 ||
op->src[0]->type == GGML_TYPE_Q6_K) {
return op->src[1]->type == GGML_TYPE_F32 && ggml_is_contiguous(op->src[0]) && ggml_is_contiguous(op->src[1]);