[Minor] Add information for CUDA kernel.

wangbiao108 · Jun 2, 2023 · 3a6dfc3 · 3a6dfc3
1 parent d6d6d2d
commit 3a6dfc3
Showing 1 changed file with 11 additions and 0 deletions.
diff --git a/awq/kernels/dequantize.cuh b/awq/kernels/dequantize.cuh
@@ -1,3 +1,14 @@
+/*
+Modified from NVIDIA FasterTransformer: https://github.com/NVIDIA/FasterTransformer/blob/main/src/fastertransformer/cutlass_extensions/include/cutlass_extensions/interleaved_numeric_conversion.h
+
+@article{lin2023awq,
+  title={AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration},
+  author={Lin, Ji and Tang, Jiaming and Tang, Haotian and Yang, Shang and Dang, Xingyu and Han, Song},
+  journal={arXiv},
+  year={2023}
+}
+*/
+
 #pragma once