ViperEkura 88751d0b08 refactor: share prefill+decode step between scheduler paths ...

- Extract _step() as the single prefill-group + task_extend + decode primitive
- _run_generation_loop and run_batch now both call it, so the two cannot drift
- run_batch now records prefix hashes (paged mode) and uses input order for
  decode, matching the loop thread

2026-08-03 13:45:27 +08:00

..

api

refactor: migrate config system to Pydantic dataclasses

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

core

refactor: share prefill+decode step between scheduler paths

2026-08-03 13:45:27 +08:00

__init__.py

refactor: rebuild KV cache with three-layer separation architecture

2026-07-30 17:19:06 +08:00

engine.py

refactor: rebuild KV cache with three-layer separation architecture

2026-07-30 17:19:06 +08:00

sample.py

perf: preallocate inference decode buffers

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