ViperEkura a1ea26d367 fix: rewrite GRPO data pipeline for offline record-level access ...

- process_list_field returns List[List[int]] preserving per-response boundaries
- GRPODataset rewritten to record-level __getitem__ (no windowing/stride)
- grpo_collate_fn pads variable-length responses into [B, G, R] tensors
- JsonlStore detects nested List[List[int]] and stores List[Tensor] per record
- Store._normalize skips nested-list keys from cumsum bookkeeping
- Pipeline._flush handles nested lists without cross-record flattening
- Export grpo_collate_fn from astrai.dataset
- 6 new GRPO tests + 2 updated builder tests, 114 total pass

2026-07-17 14:34:41 +08:00

..

data

fix: rewrite GRPO data pipeline for offline record-level access

2026-07-17 14:34:41 +08:00

inference

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

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

module

refactor : 压缩测试代码，消除重复

2026-06-19 14:54:39 +08:00

parallel

feat: 增加server, 并且修改测试单元

2026-04-02 15:05:07 +08:00

trainer

feat: add --resume flag to decouple weight loading from training resumption

2026-07-16 14:23:23 +08:00

conftest.py

refactor : replace iteration with consumed_samples

2026-06-30 18:42:42 +08:00