ViperEkura 0b661bae85 fix: remove blocking cleanup from streaming generator ...

- stream finally froze main thread on cache.task_free
- scheduler handles cleanup in next loop iteration instead

2026-08-08 13:12:40 +08:00

..

api

refactor: migrate config system to Pydantic dataclasses

2026-07-30 08:25:32 +08:00

core

perf: merge prefill warmup into _warmup_cuda_graphs

2026-08-08 13:10:58 +08:00

__init__.py

refactor: simplify inference engine and backend dispatch

2026-08-07 22:28:48 +08:00

engine.py

fix: remove blocking cleanup from streaming generator

2026-08-08 13:12:40 +08:00

sample.py

refactor: unify greedy check with _is_greedy helper

2026-08-07 14:14:15 +08:00