update directory for cutlass w8a8

Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-08-27 21:05:41 +00:00
parent c643e63f98
commit 57f2f26a05
42 changed files with 22 additions and 22 deletions
--- a/csrc/quantization/w8a8/per_token_group_quant_8bit.h
+++ b/csrc/quantization/w8a8/per_token_group_quant_8bit.h
@@ -0,0 +1,9 @@
+#pragma once
+#include <torch/all.h>
+
+// 8-bit per-token-group quantization helper used by both FP8 and INT8
+void per_token_group_quant_8bit(const torch::Tensor& input,
+                                torch::Tensor& output_q,
+                                torch::Tensor& output_s, int64_t group_size,
+                                double eps, double min_8bit, double max_8bit,
+                                bool scale_ue8m0 = false);