Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
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
4 changes: 2 additions & 2 deletions ggml/src/ggml-cuda/mmq.cu
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ static __global__ void mmq_ids_helper(
#pragma unroll
for (int offset = neu_padded; offset < warp_size; offset += neu_padded) {
const int tmp = __shfl_up_sync(0xFFFFFFFF, it_compact_add_self, offset, warp_size);
if (threadIdx.x >= offset) {
if (threadIdx.x >= static_cast<unsigned int>(offset)) {
it_compact_add_lower += tmp;
}
}
Expand Down Expand Up @@ -110,7 +110,7 @@ static __global__ void mmq_ids_helper(

expert_bounds[expert] = nex_prev;

if (expert < gridDim.x - 1) {
if (expert < static_cast<int>(gridDim.x) - 1) {
return;
}

Expand Down
2 changes: 2 additions & 0 deletions ggml/src/ggml-cuda/pad_reflect_1d.cu
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,8 @@ static __global__ void pad_reflect_1d_kernel_f32(

*(float *)(dst_ptr + i0 * nb0) = value;
}

GGML_UNUSED(ne00);
}

void ggml_cuda_op_pad_reflect_1d(ggml_backend_cuda_context & ctx, ggml_tensor * dst) {
Expand Down
Loading