Recipe
nvidia-nim-chart
NVIDIA Inference Microservice as a self-hosted, GPU-native inference server on Kubernetes through NVIDIA's own `nim-llm` Helm chart, pulled from NVIDIA's chart repository at helm.ngc.nvidia.com. Using it needs an NVIDIA account and an NGC API key, under NVIDIA's licence terms: the chart's licence file names LicenseRef-NvidiaProprietary, and it runs the NIM image infra.image names, which the reader must be entitled to pull. The catalog names no image, and the build halts until infra.image is set. The chart renders a StatefulSet giving each replica its own model-cache claim, its Service on infra.port and the headless Service beside it. An attached ngc_api_key reaches the chart as the name and data key of its Secret, so no key is rendered. The chart's connection-test Pods are left out, and its autoscaler, ingress and monitor stay off. Reach for this realization where NVIDIA's chart is wanted and its repository is reachable from the build. Reach for `nvidia-nim`, the workload synthesis, where the build must fetch nothing or a GPU runtime class is named, which this chart cannot set; reach for `nvidia-nim-service` where the NIM Operator runs.
Asal-usul
- Digest konten
- sha256:d6cf7a6063cef8a96cb769b9740e3a4f728282136bd441a06f0ce180b9881cad
- Dipublikasikan
- 2026-11-10T10:25:59Z
- Identitas penandatangan
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Tanda tangan
- 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
sha256:4dbf08dc37bd5b0742c8515e0f084276af2a05876a73a0a76320c2f520623b50
Referensi pada versi ini
oci://hub.aggrega.ai/recipe/helm/nvidia-nim-chart:1.0.0- Target
- —
- Mengimplementasikan
- core/ai-model/nvidia-nim:1.0.0
Menyediakan
Templat pointer deterministik yang dihubungkan resep ini untuk konsumen.
| Nama | Templat |
|---|---|
| host | {{ .context.rendered_name }} |
| port | {{ .infra.port }} |
| endpoint | http://{{ .context.rendered_name }}:{{ .infra.port }}/v1 |
| model | {{ .values.model }} |
| protocol | http |
| metrics_endpoint | {{ if le (int .infra.replicas) 1 }}http://{{ .context.rendered_name }}:{{ .infra.port }}/v1/metrics{{ end }} |
| metrics_service | {{ if gt (int .infra.replicas) 1 }}{{ .context.rendered_name }}{{ end }} |
| metrics_service_port | {{ if gt (int .infra.replicas) 1 }}http-openai{{ end }} |
| metrics_path | {{ if gt (int .infra.replicas) 1 }}/v1/metrics{{ end }} |
Workload
Tidak ada templat beban kerja yang dideklarasikan.
Nilai lokal
Tidak ada nilai lokal yang dideklarasikan.
Pemetaan values
Tidak ada pemetaan values yang dideklarasikan.
Relasi
Sisi bertipe ke dan dari entitas lain yang dipublikasikan. Referensi tanpa target yang dipublikasikan ditampilkan sebagai sisi yang terputus, bukan sebagai tautan.
Menggunakan
- mengimplementasikanmengimplementasikankontrak kompatibel
core/ai-model/nvidia-nim:1.0.0
Semua keluaran wajib terpenuhi dan setiap keluaran yang disediakan disebutkan dalam kontrak.
Digunakan oleh
Tidak ada apa pun di katalog yang bergantung pada entitas ini.