Skip to content

v1.0.3 release

Compare
Choose a tag to compare
@Anerudhan Anerudhan released this 31 Jan 20:37
· 19 commits to main since this release
a86ad70

[Bug fix] Fixed an issue where in some cases with padding, SDPA backward node can produce NaNs.

[Bug fix] In some older cuda toolkits, eg. cuda 11.4, float to half conversion is not implicit. This was raised in PR-57. Thanks @drisspg for reporting this. A more explicit fix using __float2half has been implemented in this patch.

[Enhancement] Accepting github PR-55. Thanks @r-barnes for the suggestion.