wang.yuqi 3e90d015ba [Frontend] Overlap preprocessing and computation for pooling models offline inference (#47699) ...

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>

2026-07-16 14:00:20 +00:00

..

__init__.py

[Frontend][1/n] Make pooling entrypoints request schema consensus | CompletionRequest (#32395)

2026-01-16 06:17:04 +00:00

io_processor.py

[Frontend] Overlap preprocessing and computation for pooling models offline inference (#47699)

2026-07-16 14:00:20 +00:00

protocol.py

[Misc] Validate Pooling cache_salt Values (#46966)

2026-07-04 10:19:28 -04:00

serving.py

[Frontend] Refine the entrypoint class's inheritance hierarchy. (#47498)

2026-07-03 10:50:06 +00:00