ViperEkura 47b3ed4e44 feat: propagate attention backend across scheduler threads ...

- InferenceEngine/Scheduler accept an explicit backend
- capture request-level attn_backend context onto Task
- split prefill/decode batches by backend instance
- ASTR_BACKEND env overrides ContextVar as process-wide policy
- report resolved backend and CUDA-graph state in benchmark

2026-08-09 13:32:40 +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

fix: isolate continuous batch decode state

2026-08-09 01:01:41 +08:00

test_engine.py

feat: propagate attention backend across scheduler threads

2026-08-09 13:32:40 +08:00

test_protocol.py

refactor: split infer core into subpackages by concern

2026-08-08 23:43:05 +08:00

test_sample.py

refactor: split infer core into subpackages by concern

2026-08-08 23:43:05 +08:00

test_scheduler.py

feat: propagate attention backend across scheduler threads

2026-08-09 13:32:40 +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: decouple task cache from PagePool and unify steady-state detection

2026-08-08 22:43:06 +08:00

test_tool_parser.py

refactor: split infer core into subpackages by concern

2026-08-08 23:43:05 +08:00