Skip to content

CUDA/HIP: fix tests/test-backend-ops #8896

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 7, 2024
Merged

CUDA/HIP: fix tests/test-backend-ops #8896

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 7 additions & 6 deletions ggml/src/ggml-cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2742,11 +2742,12 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
case GGML_OP_MUL_MAT_ID:
{
struct ggml_tensor * a = op->src[0];
if (op->op == GGML_OP_MUL_MAT) {
struct ggml_tensor * b = op->src[1];
if (a->ne[3] != b->ne[3]) {
return false;
}
struct ggml_tensor * b = op->src[1];
if (b->type == GGML_TYPE_F16 && a->type != GGML_TYPE_F16) {
return false;
}
if (op->op == GGML_OP_MUL_MAT && a->ne[3] != b->ne[3]) {
return false;
}
switch (a->type) {
case GGML_TYPE_F32:
Expand Down Expand Up @@ -2877,7 +2878,7 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
return true;
case GGML_OP_FLASH_ATTN_EXT:
#if defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)
return op->src[0]->ne[0] == 64 || op->src[0]->ne[0] == 128;
return (op->src[0]->ne[0] == 64 && op->src[1]->type == GGML_TYPE_F16) || op->src[0]->ne[0] == 128;
#else
if (op->src[0]->ne[0] == 128) {
return true;
Expand Down
Loading