COMMITS
/ train_async.py June 8, 2026
Z
Only upload per sample stats to wandb (#2027)
Zilin Zhu committed
April 24, 2026
L
refactor/ppo (#1856)
LiLei committed
March 26, 2026
Z
Fix uploading sglang metrics to wandb (#1768)
Zilin Zhu committed
March 9, 2026
Z
[docker] cherry pick qwen3.5 bugfix (#1691)
Zilin Zhu committed
March 8, 2026
S
Z
support offloading non-updatable server (#1668)
Zilin Zhu committed
January 16, 2026
Z
[cleanup] clean up utils folder (#1437)
Zilin Zhu committed
January 5, 2026
Z
[refactor] minor code refactor for save_hf (#1334)
Zilin Zhu committed
C
[Megatron Bridge] Support save hf format model (#1289)
Chenhe committed
December 18, 2025
Z
Support async save and add extra save at the end of the training (#1143)
Zilin Zhu committed
December 5, 2025
S
November 26, 2025
F
Support checking SGLang weight update correctness (#927)
fzyzcjy committed
November 17, 2025
F
Tiny unify wandb and tensorboard code (#801)
fzyzcjy committed
F
Super tiny add comments for train_async (#800)
fzyzcjy committed
F
Super tiny configure logger (#797)
fzyzcjy committed
November 16, 2025
C
[Feature] Tiny fix for wandb run id (#730)
Chengxing Xie committed
October 16, 2025
Z
fix rollout dataset loading (#504)
Zilin Zhu committed
October 13, 2025
Z
[bugfix] initialize rollout manager first to calculate num_rollout (#473)
Zilin Zhu committed
October 10, 2025
F
Allow checking accuracy correctness programmatically (#453)
fzyzcjy committed
F
Fix async training error in last rollout (#452)
fzyzcjy committed
October 5, 2025
G
Update train_async.py (#413)
Guido1Alessandro1Trevisan committed
September 28, 2025
Z
[refactor] remove Registry and change the order of init (#398)
Zilin Zhu committed
September 19, 2025
Z
[refactor] Add actor registry (#359)
Zilin Zhu committed
Z
[feat] add --critic-lr and --num-critic-only-steps (#350)
Zilin Zhu committed
September 17, 2025
Z
[feat] init support for PPO (#342)
Zilin Zhu committed
September 16, 2025
H
[Refactor] Merge rollout controller into rollout manager (#304)
Huapeng Zhou committed
August 14, 2025
August 11, 2025
Z
[refactor] separate generate and eval in Buffer to make the code cleaner (#161)
Zilin Zhu committed
Z
[refactor] move log_eval_data to Buffer (#159)
Zilin Zhu committed
July 31, 2025
C
Fix some tiny bugs and add assert (#122)
Chengxing Xie committed
July 25, 2025
F
Refactor multi-process wandb initialization logic (#100)
fzyzcjy committed
F
F
Remove Buffer data pool (#97)
fzyzcjy committed
F
Fix train_async error (#96)
fzyzcjy committed
July 15, 2025
Z
enhance: save memory by separating get_model and ddp init
Zilin Zhu committed
July 12, 2025
Z
fix sft bugs and always read data into pandas df
Zilin Zhu committed
July 11, 2025
Z
refactor: change train_agent_async.py to train_async.py and add doc
Zilin Zhu committed