ViperEkura 5c180cfa90 fix : handle zero-token batch generation ...

- return empty results without running inference for non-positive limits
- keep scheduler batch outputs aligned with requested max_tokens
- add engine and scheduler regression coverage

2026-08-06 12:31:09 +08:00

..

api

refactor: migrate config system to Pydantic dataclasses

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

core

fix : handle zero-token batch generation

2026-08-06 12:31:09 +08:00

__init__.py

feat : add radix prefix cache

2026-08-06 11:45:52 +08:00

engine.py

fix : handle zero-token batch generation

2026-08-06 12:31:09 +08:00

sample.py

perf: preallocate inference decode buffers

2026-08-03 00:55:26 +08:00