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.
This PR disables CP tests for THD format for architectures lower than sm90. In the future, we will add a utility function so users can check this before running any tests.
Type of change
[ ] Documentation change (change only to the documentation, either a fix or a new content)
[x ] 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
[ ] Code refractor
Changes
Please list the changes introduced in this PR:
Skipped tests for fused attention with THD and CP on <sm90.
Description
This PR disables CP tests for THD format for architectures lower than sm90. In the future, we will add a utility function so users can check this before running any tests.
Type of change
Changes
Please list the changes introduced in this PR:
Checklist: