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

1.61k stars 256 forks source link

Use correct FP8 group in multi-GPU docs #852

Closed timmoon10 closed 1 month ago

timmoon10 commented 1 month ago

Description

The process group for FP8 amax reductions should be the tensor-parallel group, but we use the data-parallel group in the docs for multi-GPU training. See https://github.com/NVIDIA/TransformerEngine/issues/656#issuecomment-1972000820.

Fixes https://github.com/NVIDIA/TransformerEngine/issues/656.

Type of change

[x] 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)

Changes

Use tensor-parallel group for FP8 group in multi-GPU training docs

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
[x] I have made corresponding changes to the documentation
[ ] My changes generate no new warnings
[ ] I have added tests that prove my fix is effective or that my feature works
[ ] New and existing unit tests pass locally with my changes