[Kernel] Add non-gated support for NVFP4 CUTLASS MoE (#37320)

Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2026-03-17 18:12:04 -04:00
committed by GitHub
parent 3ed7b1e6e0
commit 09e4576f65
8 changed files with 53 additions and 26 deletions
+2 -1
View File
@@ -262,7 +262,8 @@ void get_cutlass_moe_mm_data(
torch::Tensor& problem_sizes1, torch::Tensor& problem_sizes2,
torch::Tensor& input_permutation, torch::Tensor& output_permutation,
const int64_t num_experts, const int64_t n, const int64_t k,
const std::optional<torch::Tensor>& blockscale_offsets);
const std::optional<torch::Tensor>& blockscale_offsets,
const bool is_gated);
void get_cutlass_moe_mm_problem_sizes_from_expert_offsets(
const torch::Tensor& expert_first_token_offset,