9 Commits (fe5ecbd7e5f0f84de71c6b8babbd4a7467aa09fd)

Author	SHA1	Message	Date
Jiyang	fe5ecbd7e5	Merge 437eae89d6 into a3c7b01cc0	2026-09-12 07:06:16 +08:00
jingyaogong	a3c7b01cc0	[fix] keep agent rollout token-aligned #850	2026-09-10 11:44:05 +08:00
Jiyang Liu	437eae89d6	[feat] add MPS support for Apple Silicon ... On macOS there's no CUDA, so these trainer scripts fall back to CPU. Detect MPS in the --device default and switch mixed precision to the device-agnostic torch.autocast / torch.amp.GradScaler so it works there. CUDA and CPU paths are unchanged.	2026-08-14 01:26:49 +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