Esta página foi traduzida automaticamente. Ler o original em inglês.

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.

Proveniência

OficialAssinado por uma identidade de assinatura que este catálogo reconhece como editor oficial.
Digest do conteúdo
sha256:b13caeae34054f971912cfb864d53c9efbe299e59dbd5280ed7ce312e50fed52
Publicado
2026-11-10T10:09:41Z
Identidade de assinatura
https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main

Assinatura

  • Oficialapplication/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

Referência nesta versão

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

Parâmetros do programador

Valores que o programador define no Aggregate.

Estende BaseComponents#/schemas/BaseModelParameter

NomeTipoPredefiniçãoObrigatórioDescrição
served_model_namestring—não—

Dimensionamento do operador

Dimensionamento da infraestrutura que o operador ajusta por ambiente.

NomeTipoPredefiniçãoObrigatórioDescrição
portinteger (min 1024, max 65535)8000nãoServer listen port for the model API. Most operators should omit this and let the Recipe assign the default (8000).
engine_versionstringv0.6.3nãovLLM runtime image tag. Selects the image tag on the synthesized serving and weights-pull containers.
replicasinteger (min 1)1nãoNumber of serving replicas. Each replica holds its own model-cache volume and pulls the weights independently.
min_replicasinteger (min 1)—nãoLower 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)—nãoUpper 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—não—
model_cacheobject—nãoPer-replica model-weights cache volume. Sized for the pulled model; each serving replica gets its own claim.
model_artifactstring—nãoOptional 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_presentbooleanfalsenãoOperator 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)—nãoProvider-specific overrides. Accepts any nested structure. Each Recipe documents which keys it reads.
gpuobject—nãoOptional 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.

Contrato de saída

Valores que este componente publica para os consumidores através da topologia uses.

NomeTipoPredefiniçãoObrigatórioDescrição
hoststring—simIn-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—simTCP 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—simFull 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—simName 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—nãoURL scheme to reach `host` and `port` over, for a consumer composing its own address rather than reading `endpoint`.
metrics_endpointstring—nãoThe 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—nãoName 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—nãoName of the port of `metrics_service` that carries the metrics, `http`. Set and empty together with `metrics_service`.
metrics_pod_selectorstring—nãoKubernetes 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—nãoName of the container port on those pods that carries the metrics, `http`. Set and empty together with `metrics_pod_selector`.
metrics_pathstring—nãoPath 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.

Sockets uses

Os sockets de dependência através dos quais este componente se liga. O destino de cada ligação estabelecida através de um socket tem de satisfazer o respetivo seletor de etiquetas, e cada ligação pode transportar um acoplamento nos slots que o socket declara. Cada ligação que o Aggregate ou a Release estabelece através do socket tem de preencher os slots obrigatórios.

Nenhum socket uses declarado.

Slots de acoplamento

Pontos de vinculação com nome nos quais uma Feature se acopla a este componente. O seletor de um slot restringe qual a Feature que o pode preencher, e a respetiva lista inject indica como o material da Feature pode ser entregue. Um slot obrigatório tem de estar vinculado em cada instância, por um acoplamento na instância ou num âmbito acima dela, e um slot sensível é declarado para tratar material secreto. Uma Feature também se pode acoplar com um nome que nenhum slot declara.

SlotSeletorObrigatórioInjeçãoSensívelDescrição
model_pull_tokenfeature.aggrega.ai/kind=secretnãoenvsimOptional 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=secretnãoenvsimOptional 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.

Lista de autorizações de autoinjeção

env

Relações

Arestas tipadas de e para outras entidades publicadas. Uma referência sem destino publicado é apresentada como uma aresta quebrada em vez de uma ligação.

Usa

Usado por

Referência do conceito Component →

O catálogo Aggrega — um índice aberto de componentes, funcionalidades, receitas e dos plugins que os renderizam.

Criado com o sistema de design partilhado do Aggrega.

Privacidade