Using 1 confused the serverless capacity math. Set workload_calculator,
benchmark target throughput, and client cost all to 100 — the conventional
default the rest of the system expects.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The startup benchmark previously returned instantly, producing
max_throughput around 339895. A null worker has no real throughput
concept (each reservation is a unitless slot), so sleep 1s during the
benchmark with workload=1 to record max_throughput ~= 1.0.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
A held reservation runs for up to MAX_RESERVATION_SECONDS (default 1h), so
queueing a second /reserve behind it makes no sense — the wait would dwarf
any sane timeout. Set max_queue_time=0.0 so the framework rejects 429 as
soon as another reservation is in flight, and serverless routes the request
to a free worker or scales a new one up.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The held /reserve now waits on an asyncio.Event and resolves when the local
queue consumer POSTs /release on the internal control port (127.0.0.1:18999
by default). This produces a 200 success in metrics instead of the 499
cancellation you got from disconnecting the client. The duration cap stays
as a safety net for stuck consumers.
The internal aiohttp server is now unconditional and hosts /release always;
the stub /health route is added only when BACKEND_HEALTH_URL is unset.
NULL_STUB_HEALTH_PORT is renamed to NULL_CONTROL_PORT to reflect the
broader role.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds an in-process aiohttp stub on 127.0.0.1:18999/health so the framework's
periodic healthcheck has something live to talk to. Operators can override
with BACKEND_HEALTH_URL to point at their queue consumer's /health
endpoint, so the autoscaler marks the worker errored if the consumer dies.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
A PyWorker that does not forward to any model server. POST /reserve holds
the worker busy until the client disconnects (or the duration cap elapses),
so users with their own job queue can drive Vast autoscaling without
exposing inbound model traffic on the instance.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Rob Ballantyne