feat: add return_lse support for SDPA and SAGEV1 kernel — enable sequence-parallel (Ring Attention) merge (#1991)
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>