[Performance][Kernel] Fused_moe Performance Improvement (#9384)
Signed-off-by: charlifu <charlifu@amd.com>
This commit is contained in:
@@ -145,11 +145,6 @@ void dynamic_per_token_scaled_fp8_quant(
|
||||
torch::Tensor& out, torch::Tensor const& input, torch::Tensor& scale,
|
||||
c10::optional<torch::Tensor> const& scale_ub);
|
||||
|
||||
void moe_align_block_size(torch::Tensor topk_ids, int64_t num_experts,
|
||||
int64_t block_size, torch::Tensor sorted_token_ids,
|
||||
torch::Tensor experts_ids,
|
||||
torch::Tensor num_tokens_post_pad);
|
||||
|
||||
void selective_scan_fwd(const torch::Tensor& u, const torch::Tensor& delta,
|
||||
const torch::Tensor& A, const torch::Tensor& B,
|
||||
const torch::Tensor& C,
|
||||
|
||||
Reference in New Issue
Block a user