[Kernel] Use fused rmsnorm for some models like qwen3 series (#17735)
Signed-off-by: evian <eviantai@u.nus.edu> Co-authored-by: evian <eviantai@u.nus.edu>
This commit is contained in:
@@ -140,6 +140,10 @@ void rms_norm(torch::Tensor& out, // [..., hidden_size]
|
||||
torch::Tensor& input, // [..., hidden_size]
|
||||
torch::Tensor& weight, // [hidden_size]
|
||||
double epsilon) {
|
||||
TORCH_CHECK(out.is_contiguous());
|
||||
TORCH_CHECK(input.is_contiguous());
|
||||
TORCH_CHECK(weight.is_contiguous());
|
||||
|
||||
int hidden_size = input.size(-1);
|
||||
int num_tokens = input.numel() / hidden_size;
|
||||
|
||||
|
||||
Reference in New Issue
Block a user