Skip to content
Merged
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
2 changes: 0 additions & 2 deletions ggml/src/ggml-cuda/fattn-vec.cuh
Original file line number Diff line number Diff line change
Expand Up @@ -535,8 +535,6 @@ void ggml_cuda_flash_attn_ext_vec_case(ggml_backend_cuda_context & ctx, ggml_ten
float logit_softcap;
memcpy(&logit_softcap, (const float *) KQV->op_params + 2, sizeof(float));

const int cc = ggml_cuda_info().devices[ggml_cuda_get_device()].cc;

if (Q->ne[1] == 1) {
constexpr int cols_per_block = 1;
if (logit_softcap == 0.0f) {
Expand Down
4 changes: 1 addition & 3 deletions ggml/src/ggml-cuda/topk-moe.cu
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
It is intended as fusion of softmax->top-k->get_rows pipeline for MoE models
*/
template <size_t n_experts, bool with_norm>
template <int n_experts, bool with_norm>
__launch_bounds__(4 * WARP_SIZE, 1) __global__ void topk_moe_cuda(const float * logits,
float * weights,
int32_t * ids,
Expand Down Expand Up @@ -204,8 +204,6 @@ void ggml_cuda_op_topk_moe(ggml_backend_cuda_context & ctx,

GGML_ASSERT(ids->nb[1] / ggml_type_size(ids->type) == (size_t) n_experts);

cudaStream_t stream = ctx.stream();

const int n_expert_used = weights->ne[1];

if (with_norm) {
Expand Down
2 changes: 1 addition & 1 deletion ggml/src/ggml-musa/CMakeLists.txt
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ if (MUSAToolkit_FOUND)

set_source_files_properties(${GGML_SOURCES_MUSA} PROPERTIES LANGUAGE CXX)
foreach(SOURCE ${GGML_SOURCES_MUSA})
set(COMPILE_FLAGS "-fsigned-char -x musa -mtgpu")
set(COMPILE_FLAGS "-Od3 -fno-strict-aliasing -ffast-math -fsigned-char -x musa -mtgpu -fmusa-flush-denormals-to-zero")
foreach(ARCH ${MUSA_ARCHITECTURES})
set(COMPILE_FLAGS "${COMPILE_FLAGS} --cuda-gpu-arch=mp_${ARCH}")
endforeach()
Expand Down
Loading