Skip to content

CUDA backend: CUDA graph fixes for mask indexing, .item() and changed input shapes, masked copies as where, tensor checks dropped before compiling, float64, _reshape_copy, scatter_reduce and varlen_attn, follow-ups - #24326

Merged
shoumikhin merged 89 commits into
pytorch:mainfrom
shoumikhin:cuda-graph-data-dependent
Nov 2, 2026

Compare the varlen_attn decomposition with the op on CUDA only

fab02c4
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

2 warnings and 1 notice
check-labels
succeeded Nov 2, 2026 in 29s