codingma 9c0b4b3835 [v1][feature] add dpo trainer (#10544) ...

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-26 15:32:10 +08:00

..

train_batching_strategy

[v1] Fix device mesh, fix lora for reward model and fix sp (#10555)

2026-06-25 20:05:56 +08:00

train_freeze

[v1] add deepspeed zero3 trigger for low memory usage weight loading (#10300)

2026-04-21 14:09:52 +08:00

train_full

[v1] support liger_kernel (#10493)

2026-05-21 11:44:56 +08:00

train_lora

[v1][feature] add dpo trainer (#10544)

2026-06-26 15:32:10 +08:00

train_qlora

[v1] add deepspeed zero3 trigger for low memory usage weight loading (#10300)

2026-04-21 14:09:52 +08:00