Load a model when someone asks for it, and stop it when nobody does
CI / test (push) Successful in 1m29s
CI / test (push) Successful in 1m29s
The feature the idle tracking was for. A cluster with more models than GPUs can now hold every model in its catalog and only the wanted ones in its cards: min 0 with a max above it means load on demand, and once nobody has asked for idle_timeout the replicas stop and the cards go back. No new field, because min 0 max 1 already reads correctly — keep none running, allow up to one. Which made min 0 max 0 meaningful for the first time: configured and deliberately not running. normalize() used to fill a zero max in, on the reasonable ground that a model with no maximum cannot run; that would now silently turn every switched-off model into an on-demand one, including the ones already written that way in this cluster's own configuration. A model with no scaling stanza stays off for the same reason — defaulting it to on-demand would let any client request start a 70B nobody intended to run. The one real decision is what happens to the request that triggers a load. Refusing makes the feature useless, since the first request for every model fails; waiting without a bound turns a request into a job, and a client that budgeted thirty seconds holds a connection for ten minutes. So it waits briefly and then says what is happening — 503 with Retry-After and "the model is loading", which is a different answer from "no endpoint serves this" and produces different client behaviour. An unknown model still gets the unknown-model error, or on-demand would turn every typo into "loading" and the useful message would disappear. Use keeps a model alive rather than only the request that started it, without which the timer measures time since the load and a busy model is evicted on schedule however hard it is working. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
b619546516
commit
7fe59bd5fb
11 files changed
+521
-5
No files matched your search
@@ -143,6 +143,15 @@ type Control struct {
|
||||
|
||||
// Router holds routing behaviour.
|
||||
type Router struct {
|
||||
// ActivationWait is how long a request waits for an on-demand model to
|
||||
// load before the client is told to come back. Zero takes the default.
|
||||
//
|
||||
// The one real decision in on-demand loading. Refusing outright makes the
|
||||
// feature useless, since the first request for every model would fail;
|
||||
// waiting without a bound turns a request into a job, and a client that
|
||||
// budgeted thirty seconds ends up holding a connection for ten minutes.
|
||||
ActivationWait time.Duration `koanf:"activation_wait"`
|
||||
|
||||
ScrapeInterval time.Duration `koanf:"scrape_interval"`
|
||||
ScrapeTimeout time.Duration `koanf:"scrape_timeout"`
|
||||
// StaleAfter is how long an endpoint may go unscraped before being scored
|
||||
|
||||
Reference in new issue
Block a user