Commit History
Build (aarch64-linux Torch 2.8)
f207cd2
Build (x86_64-linux)
8b32f11
Build (aarch64-linux)
e6ce28c
Enable ROCm build
6677800
Sync CUDA paged-attention with upstream
4c6b316
Improve tests for mps
4dbd9c0
Update readme
16fc7e4
Add metal paged attention
ed30f9d
feat: add tag for hfjob build
a0903d3
verified
Build
1e0a970
Build (AArch64)
20990f8
Update flake inputs
daf6221
Use default CUDA capabilities
0f86240
Fix flake input
bebc17e
Build (aarch64)
a9bb8f7
Build
dde9676
Sync capabilities with upstream
3f98f45
Update flake
cea0337
feat: update to include rev in kernel for reproducible symbols
9164b48
drbh
commited on