[Perf][Kernel] Fused SiLU+Mul+Quant kernel for NVFP4 cutlass_moe (#31832)

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2026-01-09 07:40:33 -07:00
committed by GitHub
parent 8e27663b6a
commit 34cd32fe30
8 changed files with 278 additions and 95 deletions
+6
View File
@@ -301,6 +301,12 @@ void scaled_fp4_experts_quant(
torch::Tensor const& input_offset_by_experts,
torch::Tensor const& output_scale_offset_by_experts);
void silu_and_mul_scaled_fp4_experts_quant(
torch::Tensor& output, torch::Tensor& output_scale,
torch::Tensor const& input, torch::Tensor const& input_global_scale,
torch::Tensor const& input_offset_by_experts,
torch::Tensor const& output_scale_offset_by_experts);
void per_token_group_quant_fp8(const torch::Tensor& input,
torch::Tensor& output_q, torch::Tensor& output_s,
int64_t group_size, double eps, double fp8_min,