Bu sayfa makine çevirisiyle çevrilmiştir. İngilizce aslını okuyun.

Component

core/ai-model/vllm

vLLM running in-cluster as a self-hosted inference server. A Recipe synthesizes the runtime directly: a weights-pull initContainer resolves the model pointer into a model-cache volume the serving container mounts, and a ClusterIP Service fronts the OpenAI-compatible API. The model value is a deterministic pointer resolved at pod start, never fetched at compile time. Exports its host, port, endpoint, model, and protocol to consumers via the uses topology, so an agent reaches the model without hardcoding an endpoint. Each realization also publishes where Prometheus finds the server's metrics: one address as `metrics_endpoint`, or, where one address cannot reach every replica, the Service or the pod labels a scraper discovers them by. On KServe the cluster's serving runtime decides the metrics port and path, so nothing is published there. On a cluster running the Prometheus Operator, `core/prometheus-exporter` attached to the synthesized Kubernetes realization, its port set to `http`, emits a ServiceMonitor for it instead.

Köken

ResmiBu kataloğun resmi yayıncı olarak tanıdığı bir imzalama kimliğiyle imzalanmıştır.
İçerik özeti
sha256:b13caeae34054f971912cfb864d53c9efbe299e59dbd5280ed7ce312e50fed52
Yayımlanma
2026-11-10T10:09:41Z
İmzalama kimliği
https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main

İmza

  • Resmiapplication/vnd.dev.sigstore.bundle.v0.3+json

    https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main

    sha256:50a6d28f11d3c84b4ec7b3b89bbdecc5d9f1523323fda172c2340fbd633553ce

Bu sürümdeki referans

oci://hub.aggrega.ai/component/core/ai-model/vllm:1.0.0

Geliştirici parametreleri

Geliştiricinin Aggregate'te ayarladığı değerler.

BaseComponents#/schemas/BaseModelParameter öğesini genişletir

AdTipVarsayılanZorunluAçıklama
served_model_namestring—hayır—

Operatör boyutlandırması

Operatörün her ortam için ayarladığı altyapı boyutlandırması.

AdTipVarsayılanZorunluAçıklama
portinteger (min 1024, max 65535)8000hayırServer listen port for the model API. Most operators should omit this and let the Recipe assign the default (8000).
engine_versionstringv0.6.3hayırvLLM runtime image tag. Selects the image tag on the synthesized serving and weights-pull containers.
replicasinteger (min 1)1hayırNumber of serving replicas. Each replica holds its own model-cache volume and pulls the weights independently.
min_replicasinteger (min 1)—hayırLower bound for the replica count when horizontal autoscaling is configured. Declared ahead of rendering — the synth recipes serve a fixed replica count and do not yet emit an autoscaler; set it to record the intended lower bound.
max_replicasinteger (min 1)—hayırUpper bound for the replica count when horizontal autoscaling is configured. Declared ahead of rendering — the synth recipes serve a fixed replica count and do not yet emit an autoscaler; set it to record the intended upper bound.
computeobject—hayır—
model_cacheobject—hayırPer-replica model-weights cache volume. Sized for the pulled model; each serving replica gets its own claim.
model_artifactstring—hayırOptional OCI reference to the model weights, an alternative weights source to the Hugging Face model id in values.model. A deterministic pointer the runtime resolves at pod start; the compiler never fetches it. Declared ahead of rendering — the synth recipes resolve weights from values.model and do not yet consume this pointer.
control_plane_presentbooleanfalsehayırOperator affirmation that the model-serving control plane (the KServe or KubeAI controller and its custom-resource definitions) is installed in the target cluster. A controller-driven realization halts the build unless this is set true, so a serving custom resource is never emitted as an orphan into a cluster that cannot reconcile it. The direct synthesis recipes ignore this flag.
overridesobject (open)—hayırProvider-specific overrides. Accepts any nested structure. Each Recipe documents which keys it reads.
gpuobject—hayırOptional GPU scheduling for the serving container. When set, the Recipe requests GPUs as the extended resource nvidia.com/gpu and, when a runtime class is named, schedules the pod under it. Requires a GPU-capable cluster and, for runtime_class, a matching RuntimeClass configured in the cluster. Omit the whole object to serve on CPU.

Çıktı sözleşmesi

Bu bileşenin uses topolojisi üzerinden tüketicilere yayımladığı değerler.

AdTipVarsayılanZorunluAçıklama
hoststring—evetIn-cluster DNS name of the Service fronting the inference server. Which Service that is follows the realization the Manifest selected, so a consumer reads this rather than deriving a name.
portinteger—evetTCP port that Service accepts model requests on. A controller-driven realization fronts the server on its own port, so a consumer reads this rather than assuming a default.
endpointstring—evetFull base URL of the OpenAI-compatible API the server serves, with the host, the port and the API path already composed. A consumer hands it to a client library as its base URL.
modelstring—evetName a request must ask this server for. It is the served name the realization registered, which is not always the weights id the Aggregate declared.
protocolstring—hayırURL scheme to reach `host` and `port` over, for a consumer composing its own address rather than reading `endpoint`.
metrics_endpointstring—hayırThe full address Prometheus scrapes this server's metrics at — scheme, host, port and path, `http://<host>:<port>/metrics`, on the port the API is served on. Empty where one address cannot reach every replica, which then publishes the service or pod facts instead, and on KServe, which publishes none.
metrics_servicestring—hayırName of the Service every replica's metrics sit behind, for a scraper that discovers each endpoint of that Service rather than scraping one address. Set by the Kubernetes synthesis while infra.replicas is above one, beside `metrics_service_port` and `metrics_path`; empty otherwise.
metrics_service_portstring—hayırName of the port of `metrics_service` that carries the metrics, `http`. Set and empty together with `metrics_service`.
metrics_pod_selectorstring—hayırKubernetes label selector matching every pod that serves this server's metrics, for a scraper that discovers those pods directly because no Service of the realization carries them. Set by the KubeAI realization, beside `metrics_pod_port` and `metrics_path`; empty otherwise.
metrics_pod_portstring—hayırName of the container port on those pods that carries the metrics, `http`. Set and empty together with `metrics_pod_selector`.
metrics_pathstring—hayırPath the metrics are served at, `/metrics`, published beside the service or the pod facts. Empty where the server publishes `metrics_endpoint`, which carries its own path.

Uses soketleri

Bu bileşenin üzerinden bağlandığı bağımlılık soketleri. Bir soket üzerinden kurulan her bağlantının hedefi, soketin etiket seçicisini karşılamalıdır ve her bağlantı, soketin bildirdiği yuvalarda bir ek taşıyabilir. Aggregate'in veya Release'in soket üzerinden kurduğu her bağlantı, zorunlu bir yuvayı doldurmakla yükümlüdür.

uses soketi bildirilmemiş.

Ekleme yuvaları

Bir Feature'ın bu bileşene eklendiği adlandırılmış bağlama noktaları. Bir yuvanın seçicisi, onu hangi Feature'ın doldurabileceğini sınırlar ve inject listesi, Feature'ın malzemesinin nasıl iletilebileceğini belirtir. Zorunlu bir yuva, her örnekte, örnek üzerindeki veya onun üstündeki bir kapsamdaki bir ek aracılığıyla bağlanmalıdır, hassas bir yuva ise gizli malzemeyi işlemek üzere bildirilmiştir. Bir Feature, hiçbir yuvanın bildirmediği bir ad altında da eklenebilir.

YuvaSeçiciZorunluEnjeksiyonHassasAçıklama
model_pull_tokenfeature.aggrega.ai/kind=secrethayırenvevetOptional model-registry pull credential for gated model weights. When attached, the weights-pull initContainer receives it as an environment variable; unattached, weights are pulled anonymously.
api_keyfeature.aggrega.ai/kind=secrethayırenvevetOptional key the server requires of every caller. When attached, the Recipe delivers it as VLLM_API_KEY, the variable vLLM reads at startup, and each request under /v1 must then carry it as a bearer token in the Authorization header. The server checks this one key, so every caller must present the same key. Unattached, the server requires none.

Kendi kendine enjeksiyon izin listesi

env

İlişkiler

Diğer yayımlanmış varlıklara giden ve onlardan gelen tipli kenarlar. Yayımlanmış bir hedefi olmayan bir başvuru, bağlantı yerine kopuk bir kenar olarak gösterilir.

Kullanır

Kullananlar

Component kavram başvurusu →

Aggrega kataloğu — bileşenlerin, özelliklerin, tariflerin ve bunları oluşturan eklentilerin açık bir dizini.

Ortak Aggrega tasarım sistemiyle oluşturuldu.

Gizlilik