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

[Docs] Mention Megatron-LM

Browse Source
This commit is contained in:
Tri Dao 2022-12-15 19:49:04 -08:00
parent ece8f05d09
commit b78f5a392d
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
usage.md
View File

@ -18,6 +18,9 @@ PR or email us. We'd very much like to hear from you!
- Microsoft's [DeepSpeed](https://github.com/microsoft/DeepSpeed):
FlashAttention is [integrated](https://github.com/microsoft/DeepSpeed/blob/ec13da6ba7cabc44bb4745a64a208b8580792954/deepspeed/ops/transformer/inference/triton_ops.py) into DeepSpeed's inference engine.
- Nvidia's [Megatron-LM](https://github.com/NVIDIA/Megatron-LM/pull/267). This
library is a popular framework on training large transformer language models at scale.
- MosaicML [Composer](https://github.com/mosaicml/composer)
[library](https://www.mosaicml.com/blog/gpt-3-quality-for-500k). Composer is a
library for efficient neural network training.