qihuanye
9e2407cdc4
Wrap eval inference in torch.inference_mode
2026-04-09 11:11:07 +00:00
qihuanye
0f85e39690
Reduce evaluation overhead with parallel video saving
2026-04-08 13:56:57 +00:00
qihuanye
85795bd91d
Vectorize image preprocessing in stable_worldmodel policy
2026-04-08 13:48:19 +00:00
qihuanye
7c2e341d93
fp16
2026-04-08 13:40:33 +00:00
qihuanye
12ba4f4352
Optimize CEM input transfers before sample expansion
2026-04-08 13:01:24 +00:00
qihuanye
fa1c15c896
Optimize JEPA eval outputs and inference hot path
2026-04-08 12:41:21 +00:00
qihuanye
8b84251eb9
add profile frame and bf15/fp16 switch
2026-03-31 11:09:02 +00:00
quentinll
ca231f9f9d
updating readme with hugging face datasets
2026-03-26 22:53:48 -04:00
Lucas Maes
19399be69f
Merge pull request #1 from Hoiyeuhng/fix/device-agnostic-and-readme
...
fix: use proj.device instead of hardcoded cuda, fix README typos
2026-03-24 14:40:26 +01:00
Haiyang Luo
d6475e6133
fix: use proj.device instead of hardcoded cuda, fix README typos
...
- Replace hardcoded device="cuda" with proj.device in SIGReg for
portability (e.g. macOS MPS, CPU)
- Fix "Both functions accept" → "This function accepts" (only one
function is shown)
- Fix "please reference in your paper" → "please reference it in
your paper"
2026-03-23 23:30:53 -07:00
Lucas Maes
83f97d72ad
Initial commit
2026-03-23 14:22:26 +01:00
