github
/
ColossalAI
mirror of https://github.com/hpcaitech/ColossalAI
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[triton] added copyright information for flash attention (#2835) 

* [triton] added copyright information for flash attention

* polish code
pull/2871/head
Frank Lee 2023-02-21 11:25:57 +08:00 committed by GitHub
parent 7ea6bc7f69
commit 918bc94b6b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 27 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
LICENSE
View File

@ -201,17 +201,31 @@ Copyright 2021- HPC-AI Technology Inc. All rights reserved.
See the License for the specific language governing permissions and
limitations under the License.
## Some of colossal-ai's code is derived from Alpa, which is subject to the following copyright notice:
## Some of colossal-ai's code is derived from others projects, which is subject to the following copyright notice:
Copyright 2021 The Alpa team.
Copyright 2021 The Alpa team.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
https://github.com/alpa-projects/alpa/blob/979a45a3e6187df941ef4a4c4c6eea664527d68d/LICENSE
https://github.com/alpa-projects/alpa/blob/979a45a3e6187df941ef4a4c4c6eea664527d68d/LICENSE
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-------------------------------------------------
Copyright 2018-2020 Philippe Tillet
Copyright 2020-2022 OpenAI
Permission is hereby granted, free of charge, to any person obtaining
a copy of this software and associated documentation files
(the "Software"), to deal in the Software without restriction,
including without limitation the rights to use, copy, modify, merge,
publish, distribute, sublicense, and/or sell copies of the Software,
and to permit persons to whom the Software is furnished to do so,
subject to the following conditions:

15
colossalai/kernel/cuda_native/flash_attention.py
View File

@ -1,8 +1,12 @@
"""
Fused Attention
===============
This is a Triton implementation of the Flash Attention algorithm
(see: Dao et al., https://arxiv.org/pdf/2205.14135v2.pdf; Rabe and Staats https://arxiv.org/pdf/2112.05682v2.pdf; Triton https://github.com/openai/triton)
The triton-based flash attention implementation is copied from the OpenAI/triton repository
You can find the repository in Triton https://github.com/openai/triton
You can find the source file in https://github.com/openai/triton/blob/main/python/tutorials/06-fused-attention.py
Reference:
1. Dao et al., https://arxiv.org/pdf/2205.14135v2.pdf
2. Rabe and Staats https://arxiv.org/pdf/2112.05682v2.pdf
"""
import math
@ -56,7 +60,8 @@ except ImportError:
print('please install xformers from https://github.com/facebookresearch/xformers')
if HAS_TRITON:
# the following functions are adapted from the OpenAI Triton tutorial
# https://github.com/openai/triton/blob/main/python/tutorials/06-fused-attention.py
@triton.jit
def _fwd_kernel(
Q,