GitLab

* fa2 function import renaming
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* refine fa_fwd_kwargs and fa_bwd_kwargs
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* import FA3 fucntions for CP
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix output of FA3 fwd
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix rng_state in a2a implementation with FA3
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* hack lse correction for packed lse format
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* make CP thd out correction work with packed lse
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix for packed softmax_lse
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* fix softmax_lse shape
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci



* change lse_packed to constexpr
Signed-off-by: Xiaowei Ren <xren@nvidia.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci



---------
Signed-off-by: Xiaowei Ren <xren@nvidia.com>
Signed-off-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Charlene Yang <8636796+cyanguwa@users.noreply.github.com>