update directory for cutlass w8a8

Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
yewentao256
2025-08-27 21:05:41 +00:00
parent c643e63f98
commit 57f2f26a05
42 changed files with 22 additions and 22 deletions

View File

@@ -0,0 +1,12 @@
#include <ATen/cuda/CUDAContext.h>
#include <torch/all.h>
#include "../per_token_group_quant_8bit.h"
void per_token_group_quant_int8(const torch::Tensor& input,
torch::Tensor& output_q,
torch::Tensor& output_s, int64_t group_size,
double eps, double int8_min, double int8_max) {
per_token_group_quant_8bit(input, output_q, output_s, group_size, eps,
int8_min, int8_max);
}