Commit Graph
2 Commits
Author SHA1 Message Date
ViperEkura c79d34eee1 refactor: simplify training and inference interfaces
- avoid constructing model_fn more than once when reading config
- keep inference package exports focused on public entry points
- rename extra strategy arguments to strategy_kwargs
2026-08-19 20:55:13 +08:00
ViperEkura f7f14d0e5f test: add online GRPO end-to-end training test 2026-08-19 00:07:16 +08:00