Recipe
tgi
Text Generation Inference as a self-hosted inference server for local development via Docker Compose, synthesized from the Workload kind by the compose provider. A weights-pull step, running the runtime's own downloader from the serving image at the same tag, resolves the model pointer into a named model-cache volume before the server starts; the compiler never fetches weights. The server is started under the weights identifier, which is the model name published to consumers. An attached model_pull_token is rendered as the HF_TOKEN environment variable on the pull step, which is also the key the credential must publish under; unattached, weights are pulled anonymously. An attached api_key is rendered the same way as API_KEY on the serving service, and the server then requires it of every caller on its generation routes. A GPU count is honoured: the compose provider reserves that many NVIDIA GPUs for the serving service, which the Docker host must be able to hand out. Compose is single-host: the replica count and the GPU runtime class are authored all the same, and the build reports each as an unsupported-field warning naming the setting. provides.host is the compose service name, which a consumer on the same compose network resolves directly.
Provenance
- Empreinte du contenu
- sha256:957c5f867ba3afbaa0e06bd205048758f2a232c688cfeaf46213e2eba0daf764
- Publié
- 2026-11-10T10:21:06Z
- Identité de signature
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Signature
- Officielapplication/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:cc2dfa9a8128165b647879bb71193d014bd641b07e790e5766d18527afd8420d
Référence à cette version
oci://hub.aggrega.ai/recipe/compose/tgi:1.0.0- Cible
- —
- Implémente
- core/ai-model/tgi:1.0.0
Fournit
Modèles de pointeurs déterministes que cette recette câble pour les consommateurs.
| Nom | Modèle |
|---|---|
| host | {{ .context.instance_id }} |
| port | {{ .infra.port }} |
| endpoint | http://{{ .context.instance_id }}:{{ .infra.port }}/v1 |
| model | {{ .values.model }} |
| protocol | http |
| metrics_endpoint | http://{{ .context.instance_id }}:{{ .infra.port }}/metrics |
| metrics_service | |
| metrics_service_port | |
| metrics_path |
Workload
Workload · form: stateless · replicas: {{ · containers: main
Variables locales
Aucune variable locale déclarée.
Correspondance des valeurs
Aucune correspondance des valeurs déclarée.
Relations
Arêtes typées vers et depuis d’autres entités publiées. Une référence sans cible publiée s’affiche comme une arête rompue plutôt que comme un lien.
Utilise
- implémenteimplémentecontrat compatible
core/ai-model/tgi:1.0.0
Toutes les sorties obligatoires sont satisfaites et chaque sortie fournie est nommée dans le contrat.
Utilisé par
Rien dans le catalogue ne dépend de cette entité.