ViperEkura 754624acf0 feat: add online rollout framework for RL strategies ...

- RolloutRunner: generate + score responses with cached re-rollout trigger
- BaseStrategy.__call__ switches online/offline via runner injection
- GRPO/DPO implement prepare_from_rollout; aliases online_grpo/online_dpo
- TrainConfig + train.py add rollout params and CLI flags
- Tests cover generate_responses, RolloutRunner cache, shared __call__

2026-07-20 03:49:56 +08:00

..

config

feat: add online rollout framework for RL strategies

2026-07-20 03:49:56 +08:00

dataset

refactor: move sample-id indexing from dataset to store

2026-07-19 16:02:50 +08:00

extension

refactor: stride-based attn interface with layout and causal mask

2026-07-14 21:34:42 +08:00

inference

fix: memmap mode=r, tool parser json.loads, greedy decode

2026-07-19 16:38:28 +08:00

model

perf: replace paged KV cache with contiguous ContiguousCache, decode all groups

2026-07-05 11:34:36 +08:00

parallel

feat: add FSDP2Executor using torch.distributed.fsdp.fully_shard API

2026-07-20 01:46:25 +08:00

preprocessing

refactor: deduplicate preprocessing kernel and BFD packing

2026-07-19 12:27:56 +08:00

serialization

fix: memmap mode=r, tool parser json.loads, greedy decode

2026-07-19 16:38:28 +08:00

tokenize

fix: make tokenizer picklable for spawn multiprocessing

2026-07-19 11:59:55 +08:00

trainer

feat: add online rollout framework for RL strategies

2026-07-20 03:49:56 +08:00

__init__.py

chore: bump to 1.3.10

2026-07-19 16:40:27 +08:00

factory.py

fix: ForwardRef._evaluate Python 3.12 compatibility

2026-07-03 18:41:19 +08:00

protocols.py

refactor: 重构训练后端为 Executor 模式

2026-05-24 20:35:44 +08:00