f5b6d18c3d
Merge 450885c0d5 into c367572702
2026-09-14 22:28:08 +08:00
9c088dd3a5
[fix] route RL trainer forward through DDP so gradients all-reduce
...
train_grpo.py, train_ppo.py and train_agent.py wrap the policy in
DistributedDataParallel but run the loss-bearing forward through
.module, bypassing the wrapper. DDP arms its gradient all-reduce hooks
inside DistributedDataParallel.forward(), so calling .module directly
means backward() performs no all-reduce: every rank steps on purely
local gradients and the replicas silently diverge. Only rank 0 is
saved, so multi-GPU RL training quietly degrades to single-GPU
training on 1/N of the data with no error.
The supervised trainers are unaffected; they already call the wrapped
module. no_grad uses of .module (rollout generation, checkpoint
saving) are left untouched, where unwrapping is correct.
Single-GPU behaviour is unchanged: with no process group, model is the
bare module and these calls are identical to before.
2026-09-14 14:54:07 +05:30
a3c7b01cc0
[fix] keep agent rollout token-aligned #850
2026-09-10 11:44:05 +08:00
450885c0d5
feat: 添加 macOS Metal (MPS) 设备支持
...
通过条件分支实现 CUDA/MPS/CPU 三端兼容：
- 新增 get_default_device() 自动检测最优设备
- 混合精度、GradScaler、DDP 按设备类型条件启用
- CUDA 环境行为完全不变，MPS 作为新增分支
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-06 10:54:20 +08:00
3f1a7cc25b
[fix] ddp exit hang
2026-06-01 17:50:39 +08:00
4497610ec0
[fix] issue#771
2026-05-19 17:40:03 +08:00
802c15b2b4
[feat] reduce RL memory
2026-05-06 15:07:28 +08:00
10776417aa
fix: resolve CUDA OOM in train_grpo.py on GPUs with <=8GB VRAM
2026-05-06 14:14:15 +08:00
773e451b11
[fix] bugs
2026-04-27 19:16:08 +08:00
6361510016
[fix] rollout bugs
2026-04-27 17:54:09 +08:00
5416a44471
[fix] bugs
2026-04-21 13:03:34 +08:00
101d7df2da
[update] minimind-3
2026-03-25 23:57:45 +08:00
cf4b49a348
[fix] align log/save last-step check and ETA with 1-indexed step
2026-03-24 02:01:40 +01:00
d25500d363
[fix] gradient accumulation step alignment
2026-03-24 01:45:04 +01:00
fea69cf338
[fix] data skip
2026-01-18 16:56:29 +08:00
f7ffdf1fdb
[update] shuffle data
2026-01-18 16:39:34 +08:00
e119db8478
[fix] compile unpack
2026-01-14 20:13:32 +08:00
81d24a4f16
[feat] add compile
2026-01-14 14:42:30 +08:00
42a4e8c86a
[fix] dist cleanup
2026-01-02 22:25:55 +08:00
9d898576ac
[update] aux loss
2026-01-01 22:41:46 +08:00
c65335b56f
[fix] experts unused
2025-12-31 21:47:04 +08:00
5dd4df7e18
[fix] moe unused
2025-12-31 21:00:06 +08:00
7eae14f3ce
[feat] remove empty_cache
2025-12-27 07:14:36 +08:00
5e1447b913
[fix] cuda memory #559
2025-12-01 16:17:43 +08:00
509d8dacf1
[feat] clear cache
2025-11-06 13:12:28 +08:00
bf123b585d
[feat] add args
2025-10-30 10:05:12 +08:00
1713c24114
[fix] model device
2025-10-29 10:36:28 +08:00
8f7e07b8ef
[feat] update trainer
2025-10-28 23:30:10 +08:00
e8484874f5
[feat] pause-training
2025-10-26 18:49:52 +08:00
a82526da11
[feat] shuffle data
2025-10-23 20:13:28 +08:00
805744e60a
[fix] loss-issues-430
2025-10-23 19:08:42 +08:00
463044e92a
[fix] sampler-ddp
2025-10-23 15:03:19 +08:00
fa7dff8291
[fix] graph-oom & ddp-pos_cis
2025-10-23 14:22:13 +08:00
7d877db79b
[feat] minimind-2510
2025-10-21 21:19:47 +08:00
Walle1999
basil-k-aji-dev
jingyaogong
shiguoliang
TKiteRunner
jingyaogong
readlnh