[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:
@@ -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,
|
||||
|
||||
Reference in New Issue
Block a user