Gahow Wang 3ae99293fd Relax _push_allowed: gate on request size, not cache savings
The old gate blocked offload when push_new (= input - cache_hit) < 20K,
which prevented migration of high-cache sessions — exactly the ones
that benefit most. After PD-sep, the target receives full KV via RDMA
and has the same cache as the source, so cache_hit is irrelevant to
the offload decision.

New gate: only check input_length >= heavy_threshold (request must be
HEAVY) and max_offload_inflight (concurrency cap). Let the cost model
decide whether the contention difference justifies migration.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-05-25 00:03:28 +08:00
Description
No description provided
48 MiB
Languages
Python 82.9%
Shell 17.1%