qihuanye
|
113e591899
|
多机调整
|
2026-05-17 20:49:33 +08:00 |
|
qihuanye
|
0164e21f48
|
多机
|
2026-05-17 19:23:31 +08:00 |
|
qihuanye
|
02080e2564
|
在正式测试前添加warm up
|
2026-05-16 14:53:58 +00:00 |
|
qihuanye
|
cf43af0729
|
更改求解器 step=150时 成功率更高 step=125时 速度更快 成功率持平
|
2026-05-04 07:55:13 +00:00 |
|
qihuanye
|
75a5d86966
|
调整配置 启动视频写入开关
|
2026-04-10 03:44:09 +00:00 |
|
qihuanye
|
8ba5bc8b0b
|
多卡
|
2026-04-10 03:13:54 +00:00 |
|
qihuanye
|
38be7d3bef
|
Optimize inference path: add predictor-only torch.compile with reduce-overhead
|
2026-04-09 11:11:07 +00:00 |
|
qihuanye
|
f2750daace
|
取消视频保存
|
2026-04-09 11:11:07 +00:00 |
|
qihuanye
|
9e2407cdc4
|
Wrap eval inference in torch.inference_mode
|
2026-04-09 11:11:07 +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 |
|
Lucas Maes
|
83f97d72ad
|
Initial commit
|
2026-03-23 14:22:26 +01:00 |
|