GeekExplorer f64d821c20 fix chunked prefill bugs and refactor

2026-04-26 02:53:06 +08:00

..

engine

fix chunked prefill bugs and refactor

2026-04-26 02:53:06 +08:00

layers

support chunked prefill and fix minor bug

2026-04-14 03:05:35 +08:00

models

support chunked prefill and fix minor bug

2026-04-14 03:05:35 +08:00

utils

enable slots=True for dataclasses

2026-02-08 23:46:01 -05:00

__init__.py

better

2025-06-15 10:36:45 +08:00

config.py

support chunked prefill and fix minor bug

2026-04-14 03:05:35 +08:00

llm.py

support tensor parallel

2025-06-15 01:31:24 +08:00

sampling_params.py

enable slots=True for dataclasses

2026-02-08 23:46:01 -05:00