Scale and place by what a replica was measured to serve
Release / build (push) Successful in 1m8s
CI / test (push) Successful in 4m24s
Release / notes (push) Successful in 3s

Stored ctl bench results reach the reconciler: requests per replica past
the measured SLO concurrency scale a model up, a replica is taken back only
if the rest stay under 70% of theirs, and among profiles of equal priority
the most measured tokens per GPU or core is tried first. ctl model target
sizes a model for a throughput against the room there is.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-09-30 18:21:08 +02:00
1 parent 9dc1b62fdc
commit 78e41460f9
16 files changed
+503 -15

No files matched your search

+4 -1
View File
@@ -60,6 +60,7 @@ func (a *API) Register(mux *http.ServeMux) {
mux.HandleFunc("POST /api/v1/models/{name}/scale", a.scaleModel)
mux.HandleFunc("POST /api/v1/models/{name}/resources", a.setResources)
a.registerQuotas(mux)
mux.HandleFunc("GET /api/v1/models/{name}/target", a.target)
mux.HandleFunc("POST /api/v1/models/{name}/class", func(w http.ResponseWriter, r *http.Request) {
if a.models == nil {
writeError(w, http.StatusNotImplemented, "this control plane has no store")
@@ -399,6 +400,8 @@ type HeadroomView struct {
Limited bool `json:"limited,omitempty"`
// Blocked says why one more does not fit, a line per node considered.
Blocked []string `json:"blocked,omitempty"`
// TokPerSec is what one more replica was measured to serve; 0 unmeasured.
TokPerSec float64 `json:"tok_per_sec,omitempty"`
}
// RejectionView is one rejected candidate.
@@ -958,7 +961,7 @@ func (a *API) Headroom(model string, limit int) (HeadroomView, bool) {
return HeadroomView{}, false
}
return HeadroomView{Model: model, Current: h.Current, More: h.More, Nodes: h.Nodes,
Limited: h.Limited, Blocked: h.Blocked}, true
Limited: h.Limited, Blocked: h.Blocked, TokPerSec: h.TokPerSec}, true
}
func (a *API) Explain(model string) ExplainView {