本页面为机器翻译。阅读英文原文。

Component

core/ai-model/tgi

Text Generation Inference 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 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 Recipe also publishes where Prometheus finds the server's metrics: one address as `metrics_endpoint`, or, while the Kubernetes realization runs more than one replica, the Service a scraper discovers every replica behind. On a cluster running the Prometheus Operator, `core/prometheus-exporter` attached with its port set to `http` emits a ServiceMonitor for it instead.

来源

官方由本目录认定为官方发布者的签名身份签名。
内容摘要
sha256:19e35931d9753f81e3143869dcffd919cf89b93a2770da756bbadc8066853021
发布时间
2026-11-10T10:09:37Z
签名身份
https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main

签名

  • 官方application/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

    sha256:46a2f0e5c8b71d3f5bff94a62a3523fdb3f5b0b89eac6aac1b53f1705bdd5090

此版本的引用

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

开发者参数

开发者在 Aggregate 中设置的值。

扩展 BaseComponents#/schemas/BaseModelParameter

运维规格

运维人员按环境调整的基础设施规格。

名称类型默认值必需描述
portinteger (min 1024, max 65535)8080否Server listen port for the model API. Most operators should omit this and let the Recipe assign the default (8080).
engine_versionstring3.0.1否Text Generation Inference runtime image tag. Selects the image tag on the synthesized serving and weights-pull containers.
replicasinteger (min 1)1否Number of serving replicas. Each replica holds its own model-cache volume and pulls the weights independently.
min_replicasinteger (min 1)—否Lower 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)—否Upper 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—否—
model_cacheobject—否Per-replica model-weights cache volume. Sized for the pulled model; each serving replica gets its own claim.
model_artifactstring—否Optional 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.
overridesobject (open)—否Provider-specific overrides. Accepts any nested structure. Each Recipe documents which keys it reads.
gpuobject—否Optional 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.

输出契约

此组件通过 uses 拓扑向使用方发布的值。

名称类型默认值必需描述
hoststring—是In-cluster DNS name of the Service fronting the inference server. A consumer that composes its own address dials this name; one that does not reads `endpoint` instead.
portinteger—是TCP port that Service accepts generation requests on. It follows the port an operator set in the Release, so a consumer reads it rather than assuming a default.
endpointstring—是Full base URL of the generation API, with the host, the port and the API path already composed. A consumer hands it to a client library as its base URL.
modelstring—是Name a request must ask this server for, which is the model whose weights it loaded rather than a provider catalogue name.
protocolstring—否URL scheme to reach `host` and `port` over, for a consumer composing its own address rather than reading `endpoint`.
metrics_endpointstring—否The 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 while the Kubernetes realization runs more than one replica, which then publishes `metrics_service` instead.
metrics_servicestring—否Name 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 realization while infra.replicas is above one, beside `metrics_service_port` and `metrics_path`; empty otherwise.
metrics_service_portstring—否Name of the port of `metrics_service` that carries the metrics, `http`. Set and empty together with `metrics_service`.
metrics_pathstring—否Path the metrics are served at, `/metrics`, published beside `metrics_service`. Empty where the server publishes `metrics_endpoint`, which carries its own path.

uses 套接字

此组件用于建立连接的依赖套接字。通过某个套接字接入的每个连接,其目标都必须满足该套接字的标签选择器,且每个连接都可以在该套接字声明的槽位中携带附加项。必需槽位须由 Aggregate 或 Release 通过该套接字接入的每个连接来填充。

未声明 uses 套接字。

附加槽位

Feature 附加到此组件时所用的命名绑定点。槽位的选择器限定哪个 Feature 可以填充该槽位,其 inject 列表则指明 Feature 的内容可以如何交付。必需槽位必须在每个实例上完成绑定,可以通过实例上的附加,也可以通过其上层作用域的附加;敏感槽位则声明为用于处理机密内容。Feature 也可以以任何槽位都未声明的名称进行附加。

槽位选择器必需注入敏感描述
model_pull_tokenfeature.aggrega.ai/kind=secret否env是Optional 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=secret否env是Optional key the server requires of every caller. When attached, the Recipe delivers it as API_KEY, the variable Text Generation Inference reads at startup, and each generation request 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. Text Generation Inference accepts the key whatever its letter case, so two keys differing only in case are one key to it, and a key's strength is judged on its case-folded form. Unattached, the server requires none.

自注入允许列表

env

关系

与其他已发布实体之间的类型化边。没有已发布目标的引用会呈现为断开的边,而不是链接。

使用

被使用

Component 概念参考 →

Aggrega 目录 — 收录组件、功能、配方以及渲染它们的插件的开放索引。

基于共享的 Aggrega 设计系统构建。

隐私