squall/flash-attention
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add paddlepaddle in usage

Browse Source
This commit is contained in:
kuizhiqing 2023-04-04 14:15:51 +08:00
parent d6fc860573
commit c5be8d3aab
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
usage.md
View File

@ -27,6 +27,8 @@ PR or email us. We'd very much like to hear from you!
- EleutherAI's [GPT-NeoX](https://github.com/EleutherAI/gpt-neox/pull/725). This is a research library for training large language transformer models at scale based on NVIDIA's Megatron-LM and Microsoft's DeepSpeed. - EleutherAI's [GPT-NeoX](https://github.com/EleutherAI/gpt-neox/pull/725). This is a research library for training large language transformer models at scale based on NVIDIA's Megatron-LM and Microsoft's DeepSpeed.
- PaddlePaddle: integrated into the framework with [API](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/nn/functional/flash_attention.py) `paddle.nn.functional.flash_attention`.
## MLPerf benchmarks ## MLPerf benchmarks
[MLPerf](https://mlcommons.org/en/) is a competitive machine learning performance benchmark. FlashAttention [MLPerf](https://mlcommons.org/en/) is a competitive machine learning performance benchmark. FlashAttention