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

Recipe

vllm

vLLM as a self-hosted inference server for local development via Docker Compose. Synthesized-mode Workload: the image, the command line, the environment, the model-cache volume and the weights-pull step are translated from the Workload kind by the compose provider. The weights pull is an init container, so it becomes a run-to-completion service that the serving service waits on before it starts. The model value is a deterministic pointer that step resolves at start; the compiler never fetches weights. Both services mount the same named model-cache volume, so the weights outlive the containers and a restart re-runs the pull step against an already-populated cache — how the downloader reconciles that is the downloader's own behaviour. When the optional model_pull_token credential slot is attached its value arrives on the inject pipe and is rendered as the HF_TOKEN environment variable on the weights-pull service, which is therefore also the key the attached credential must publish under; unattached, no such variable is emitted and weights are pulled anonymously. An attached api_key is rendered the same way as VLLM_API_KEY on the serving service, and the server then requires it of every caller under /v1. A GPU count is reserved as that many NVIDIA GPUs for the serving service, which the Docker host must provide. Compose is single-host, so the replica count and the GPU runtime class the Kubernetes realization honours are not honoured here; the build reports each as an unsupported-field warning naming the setting rather than dropping it in silence. provides.host is the compose service name, which a consumer on the same compose network resolves directly.

Procedência

OficialAssinado por uma identidade de assinatura que este catálogo reconhece como publicador oficial.
Digest do conteúdo
sha256:c28c526c53c3493724e66dd87738ab3f4d13555f15acd0c558dd9a2f70d5ecbc
Publicado
2026-11-10T10:21:30Z
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:e91af8a7f9d69936f300bfb1f65c533703b680658ffbbe37ba386ecbccd012bf

Referência nesta versão

oci://hub.aggrega.ai/recipe/compose/vllm:1.0.0
Destino
—
Implementa
core/ai-model/vllm:1.0.0

Fornece

Modelos de ponteiros determinísticos que esta receita liga para os consumidores.

NomeModelo
host{{ .context.instance_id }}
port{{ .infra.port }}
endpointhttp://{{ .context.instance_id }}:{{ .infra.port }}/v1
model{{ default .values.model .values.served_model_name }}
protocolhttp
metrics_endpointhttp://{{ .context.instance_id }}:{{ .infra.port }}/metrics
metrics_service
metrics_service_port
metrics_pod_selector
metrics_pod_port
metrics_path

Workload

Workload · form: stateless · replicas: {{ · containers: main

Variáveis locais

Nenhuma variável local declarada.

Mapeamento de valores

Nenhum mapeamento de valores declarado.

Relações

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

Usa

  • implementaimplementacontrato compatível

    core/ai-model/vllm:1.0.0

    Todas as saídas obrigatórias são atendidas e cada saída fornecida é nomeada no contrato.

Usado por

Nada no catálogo depende desta entidade.

Referência do conceito Recipe →

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

Criado com o sistema de design compartilhado do Aggrega.

Privacidade