CharlesCheung996
|
32d15a9932
|
Merge 744f16d802 into a3c7b01cc0
|
2026-09-10 15:51:58 +08:00 |
jingyaogong
|
a3c7b01cc0
|
[fix] keep agent rollout token-aligned #850
|
2026-09-10 11:44:05 +08:00 |
mengxin
|
fce15c0bf4
|
feat: enable MPS across training entrypoints
|
2026-09-06 03:14:06 +08:00 |
jingyaogong
|
3f1a7cc25b
|
[fix] ddp exit hang
|
2026-06-01 17:50:39 +08:00 |
jingyaogong
|
4497610ec0
|
[fix] issue#771
|
2026-05-19 17:40:03 +08:00 |
jingyaogong
|
802c15b2b4
|
[feat] reduce RL memory
|
2026-05-06 15:07:28 +08:00 |
jingyaogong
|
6361510016
|
[fix] rollout bugs
|
2026-04-27 17:54:09 +08:00 |
jingyaogong
|
5416a44471
|
[fix] bugs
|
2026-04-21 13:03:34 +08:00 |
jingyaogong
|
101d7df2da
|
[update] minimind-3
|
2026-03-25 23:57:45 +08:00 |