AstrAI/tests/inference
ViperEkura d08a92c7bd feat: add frequency penalty to inference sampling pipeline
- Add FrequencyPenaltyStrategy (logit -= penalty * count)
- Per-task rep_window for penalty history lookup
- Wire through engine, task, executor, API layer
- Add --frequency_penalty and --rep_window to stream_chat.py
- 9 unit tests for frequency penalty strategy
2026-07-17 21:28:31 +08:00
..
conftest.py refactor : FastAPI 懒加载单例,消除模块级副作用 2026-06-04 15:52:27 +08:00
test_cache.py perf: replace paged KV cache with contiguous ContiguousCache, decode all groups 2026-07-05 11:34:36 +08:00
test_engine.py refactor: 重构 inference 模块架构,引入设计模式并分组文件 2026-05-14 17:42:37 +08:00
test_protocol.py feat : BaseToolParser.feed 增加可选 token_ids 参数 2026-06-06 11:19:30 +08:00
test_sample.py feat: add frequency penalty to inference sampling pipeline 2026-07-17 21:28:31 +08:00
test_scheduler.py test: 补充推理协议层单测覆盖 2026-05-26 00:21:52 +08:00
test_server.py refactor : FastAPI 懒加载单例,消除模块级副作用 2026-06-04 15:52:27 +08:00
test_task.py refactor: 重构 inference 模块架构,引入设计模式并分组文件 2026-05-14 17:42:37 +08:00
test_tool_parser.py refactor : 压缩测试代码,消除重复 2026-06-19 14:54:39 +08:00