ViperEkura 849e1e00a3 refactor: clean up inference design patterns ...

1. KVCache base: add default task_cached/task_record_hashes, remove getattr from scheduler
2. Remove page_size param from scheduler constructor (ContiguousCache-only)
3. InferenceEngine expose cache param for KVCache injection
4. Rename page_cache -> kv_cache in Executor
5. Move stream_callback from Task to TaskManager._callbacks dict
6. TaskManager.clear_queues clears callbacks

2026-07-05 11:41:54 +08:00

..

__init__.py

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

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

cache.py

refactor: clean up inference design patterns

2026-07-05 11:41:54 +08:00

executor.py

refactor: clean up inference design patterns

2026-07-05 11:41:54 +08:00

scheduler.py

refactor: clean up inference design patterns

2026-07-05 11:41:54 +08:00

task.py

refactor: clean up inference design patterns

2026-07-05 11:41:54 +08:00