[NVIDA] [1/N] Nvfp4 Masked Gemm: Add quant op for the flashinfer grouped gemm (#9200)

2025-08-22 12:19:45 -07:00
parent f556ac8bd8
commit e5638573c1
7 changed files with 420 additions and 13 deletions
--- a/sgl-kernel/include/sgl_kernel_ops.h
+++ b/sgl-kernel/include/sgl_kernel_ops.h
@@ -389,6 +389,14 @@ 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,
+    torch::Tensor const& mask);
 /*
 * From csrc/moe/cutlass_moe/w4a8
 */