ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages 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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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]);