[Perf] Cuda Kernel for Int8 Per Token Group Quant (#21476)

Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye
2025-07-25 17:07:07 -07:00
committed by GitHub
parent 41d3082c41
commit 75d29cf4e1
6 changed files with 47 additions and 3 deletions
+5
View File
@@ -292,6 +292,11 @@ 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,
double fp8_max, bool scale_ue8m0);
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);
#endif
void static_scaled_int8_quant(torch::Tensor& out, torch::Tensor const& input,