biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Refactor] Remove unused cutlass moe problem size function (#32047)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye
2026-01-18 15:46:59 -05:00
committed by GitHub
parent 16de822c71
commit eebc58df0c
5 changed files with 0 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
csrc/quantization/w8a8/cutlass/moe/moe_data.cu
View File

@@ -130,26 +130,6 @@ inline void launch_compute_problem_sizes(const torch::Tensor& topk_ids,
}
} // namespace
void get_cutlass_moe_mm_problem_sizes_caller(
const torch::Tensor& topk_ids, torch::Tensor& problem_sizes1,
torch::Tensor& problem_sizes2, const int64_t num_experts, const int64_t n,
const int64_t k, const std::optional<torch::Tensor>& blockscale_offsets,
std::optional<bool> force_swap_ab = std::nullopt) {
auto stream = at::cuda::getCurrentCUDAStream(topk_ids.device().index());
auto options_int32 =
torch::TensorOptions().dtype(torch::kInt32).device(topk_ids.device());
torch::Tensor atomic_buffer = torch::zeros(num_experts, options_int32);
// Swap-AB should be disabled for FP4 path
bool may_swap_ab =
force_swap_ab.value_or((!blockscale_offsets.has_value()) &&
(topk_ids.numel() <= SWAP_AB_THRESHOLD));
launch_compute_problem_sizes(topk_ids, problem_sizes1, problem_sizes2,
atomic_buffer, num_experts, n, k, stream,
may_swap_ab);
}
template <bool SWAP_AB>
__global__ void compute_problem_sizes_from_expert_offsets(
const int64_t* __restrict__ expert_first_token_offset,

27
csrc/quantization/w8a8/cutlass/scaled_mm_entry.cu
View File

@@ -77,12 +77,6 @@ void get_cutlass_moe_mm_data_caller(
const int64_t num_experts, const int64_t n, const int64_t k,
const std::optional<torch::Tensor>& blockscale_offsets);
void get_cutlass_moe_mm_problem_sizes_caller(
const torch::Tensor& topk_ids, torch::Tensor& problem_sizes1,
torch::Tensor& problem_sizes2, const int64_t num_experts, const int64_t n,
const int64_t k, const std::optional<torch::Tensor>& blockscale_offsets,
std::optional<bool> force_swap_ab = std::nullopt);
void get_cutlass_moe_mm_problem_sizes_from_expert_offsets_caller(
const torch::Tensor& expert_first_token_offset,
torch::Tensor& problem_sizes1, torch::Tensor& problem_sizes2,
@@ -306,27 +300,6 @@ void get_cutlass_moe_mm_data(
version_num, ". Required capability: 90, 100, or 120");
}
void get_cutlass_moe_mm_problem_sizes(
const torch::Tensor& topk_ids, torch::Tensor& problem_sizes1,
torch::Tensor& problem_sizes2, const int64_t num_experts, const int64_t n,
const int64_t k, const std::optional<torch::Tensor>& blockscale_offsets,
std::optional<bool> force_swap_ab = std::nullopt) {
int32_t version_num = get_sm_version_num();
#if (defined ENABLE_CUTLASS_MOE_SM90 && ENABLE_CUTLASS_MOE_SM90) || \
(defined ENABLE_CUTLASS_MOE_SM100 && ENABLE_CUTLASS_MOE_SM100) || \
(defined ENABLE_CUTLASS_MOE_SM120 && ENABLE_CUTLASS_MOE_SM120)
get_cutlass_moe_mm_problem_sizes_caller(topk_ids, problem_sizes1,
problem_sizes2, num_experts, n, k,
blockscale_offsets, force_swap_ab);
return;
#endif
TORCH_CHECK_NOT_IMPLEMENTED(
false,
"No compiled get_cutlass_moe_mm_problem_sizes: no cutlass_scaled_mm "
"kernel for CUDA device capability: ",
version_num, ". Required capability: 90, 100, or 120");
}
void get_cutlass_moe_mm_problem_sizes_from_expert_offsets(
const torch::Tensor& expert_first_token_offset,
torch::Tensor& problem_sizes1, torch::Tensor& problem_sizes2,