 AlpinDale
|
e14223dce5
kernel: use `cub::BlockReduce` instead of custom impl (#895)
|
3 weeks ago |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
8 months ago |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
11 months ago |
|
AlpinDale
|
b9b295d74e
chore: backlogs 1 (#191)
|
1 year ago |
|
AlpinDale
|
7612f33afd
feat: fused add RMSNorm kernels (#125)
|
1 year ago |
|
AlpinDale
|
3d72f05c7b
feat: flattened 1D tensor -> 2D tensor (#85)
|
1 year ago |
 AlpinDale
|
32844c1522
add GELU kernels and remove compile bloat
|
1 year ago |
|
AlpinDale
|
081545bde6
fix: various CUDA kernel tweaks
|
1 year ago |
|
AlpinDale
|
b8f4337c5b
chore: various fixes
|
1 year ago |
|
AlpinDale
|
0ec53128b6
feat: add layernorm kernels
|
1 year ago |
