Skip to content

cuda : fix buffer type check with integrated GPUs #14069

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
Jun 8, 2025
Merged

cuda : fix buffer type check with integrated GPUs #14069

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
5 changes: 1 addition & 4 deletions ggml/src/ggml-cuda/ggml-cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1144,7 +1144,6 @@ typedef void (*ggml_cuda_op_mul_mat_t)(
static cudaError_t ggml_cuda_cpy_tensor_2d(
void * dst, const struct ggml_tensor * src, int64_t i3, int64_t i2, int64_t i1_low, int64_t i1_high, cudaStream_t stream) {

GGML_ASSERT(ggml_backend_buffer_is_cuda(src->buffer));
const char * src_ptr = (const char *) src->data;
char * dst_ptr = (char *) dst;

Expand Down Expand Up @@ -1427,8 +1426,6 @@ static void ggml_cuda_op_mul_mat(
const int64_t nb2 = dst->nb[2];
const int64_t nb3 = dst->nb[3];

GGML_ASSERT(ggml_backend_buffer_is_cuda(dst->buffer));
GGML_ASSERT(ggml_backend_buffer_is_cuda(src1->buffer));
ggml_backend_cuda_buffer_context * src1_ctx = (ggml_backend_cuda_buffer_context *) src1->buffer->context;
ggml_backend_cuda_buffer_context * dst_ctx = (ggml_backend_cuda_buffer_context *) dst->buffer->context;

Expand Down Expand Up @@ -1750,7 +1747,7 @@ static void ggml_cuda_mul_mat_batched_cublas(ggml_backend_cuda_context & ctx, co
GGML_ASSERT(!ggml_is_transposed(src0));
GGML_ASSERT(!ggml_is_transposed(src1));

GGML_ASSERT(ggml_backend_buffer_is_cuda(src0->buffer));
GGML_ASSERT(!ggml_backend_buft_is_cuda_split(src0->buffer->buft));
GGML_ASSERT(src0->type == GGML_TYPE_F16);

// Byte offsets and tensor dimensions are currently used in an inconsistent way for dst.
Expand Down
Loading