NVIDIA / TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

https://docs.nvidia.com/deeplearning/transformer-engine/user-guide/index.html

Apache License 2.0

2k stars 333 forks source link

[C] Separating cudnn common utils from fused_attn #1314

Closed phu0ngng closed 2 weeks ago

phu0ngng commented 3 weeks ago

Description

In this PR, the common cudnn helpers are moved out of fused attention so that they can be used in other kernels, i.e. the coming normalization.

Fixes # (issue)

Type of change

[ ] Documentation change (change only to the documentation, either a fix or a new content)
[ ] Bug fix (non-breaking change which fixes an issue)
[ ] New feature (non-breaking change which adds functionality)
[ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
[ ] Infra/Build change
[x] Code refactor

Checklist:

[x] I have read and followed the contributing guidelines
[x] The functionality is complete
[ ] I have commented my code, particularly in hard-to-understand areas
[ ] I have made corresponding changes to the documentation
[x] My changes generate no new warnings
[ ] I have added tests that prove my fix is effective or that my feature works
[x] New and existing unit tests pass locally with my changes

phu0ngng commented 3 weeks ago

/te-ci pytorch

phu0ngng commented 3 weeks ago

/te-ci pytorch