[Kernel] CUTLASS MoE FP8: Integrate cuda moe permute/unpermute (#23045)

Signed-off-by: Shixian Cui <shixian@amazon.com>
This commit is contained in:
shixianc
2025-08-20 10:35:26 -04:00
committed by GitHub
parent 4449235843
commit b17109beea
15 changed files with 369 additions and 121 deletions
+5
View File
@@ -229,6 +229,11 @@ void get_cutlass_moe_mm_data(
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(
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);
void get_cutlass_pplx_moe_mm_data(torch::Tensor& expert_offsets,
torch::Tensor& problem_sizes1,
torch::Tensor& problem_sizes2,