ViperEkura 9bcd696580 fix: token-level ratio and prompt masking in GRPO strategy ... - Mask prompt tokens to 0 so their logprobs excluded from ratio/KL - Switch to token-level ratio + PPO clipping via reduction='none' - Slice response token logprobs from full sequence output - Replace k3 KL estimator with non-negative k1 estimator - Fix epsilon from finifo.eps (~1e-38) to 1e-8 - Remove unused 'reduction' param from GRPOStrategy.__init__ - Clarify offline batch semantics in docstring - Add 11 unit tests for masking, advantage, KL, sync, clipping - Sync training.md and architecture.md docs		2026-07-12 21:24:09 +08:00
..
config	fix : SFT pipeline position_ids default & doc boundary preservation	2026-07-04 15:59:11 +08:00
dataset	feat: add JSONL dataset store with on-the-fly tokenization	2026-07-04 15:42:33 +08:00
extension	feat: wire up paged decode CUDA kernel to Python extension	2026-07-11 18:40:49 +08:00
inference	refactor: clean up inference design patterns	2026-07-05 11:41:54 +08:00
model	perf: replace paged KV cache with contiguous ContiguousCache, decode all groups	2026-07-05 11:34:36 +08:00
parallel	fix: auto-assign free port in spawn_parallel_fn to avoid EADDRINUSE	2026-07-12 19:21:56 +08:00
preprocessing	refactor: split mask builder by single/multi output	2026-07-08 21:18:34 +08:00
serialization	fix: support single .h5 file loading in load_h5	2026-07-07 00:11:16 +08:00
tokenize	refactor : Pipeline 去除去重，ids 重命名为 sequence，泛型透传	2026-05-31 15:14:27 +08:00
trainer	fix: token-level ratio and prompt masking in GRPO strategy	2026-07-12 21:24:09 +08:00
__init__.py	chore: bump version to 1.3.9	2026-07-12 21:04:20 +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