laoyao0822 69ca7045ea Preserve chunked request affinity state ...

The affinity scheduler needs to know whether the current batch is led by a chunked request. The rebase carried call sites that referenced an old private field name, while PrefillAdder only retained a boolean flag, causing startup failure before scheduling could run.

Constraint: CP bs>1 affinity must classify a chunked-led batch without reopening chunked-tail mixing behavior.

Rejected: Recreate the old private _chunked_req_in_batch attribute | keeps a stale name and hides the public state transition in PrefillAdder.

Confidence: high

Scope-risk: narrow

Directive: Keep chunked_req_in_batch and has_chunked_req_in_batch updated together when adding new chunked admission paths.

Tested: Remote cjy-glm5-new: PYTHONPATH=python python -m pytest -q test/registered/unit/managers/test_prefill_adder.py -> 26 passed; combined run with scheduler load accounting tests -> 27 passed.

Not-tested: Full ETE restart after this commit alone.

2026-06-13 02:34:55 +08:00

45 KiB

Raw Blame History

View Raw