OCI Generative AI Dedicated AI Cluster

oci ML inferenceoci-generative-ai-cluster

Single-tenant GPU capacity that hosts model endpoints or runs fine-tuning.

Provider: oci
Kind: ML inference
Category: Compute
Official docs: https://docs.oracle.com/en-us/iaas/Content/generative-ai/create-ai-cluster-hosting.htm

Properties · 5 set by this component

property	type	values	required	kind default	this component
accelerator	enum	none \| gpu \| asic	no	none	▸ gpu
acceleratorModel · advanced	enum	nvidia-h100 \| nvidia-h200 \| nvidia-b200 \| nvidia-l4 \| nvidia-a100 \| amd-mi300x \| aws-trainium \| aws-inferentia \| google-tpu \| intel-gaudi \| groq-lpu \| cerebras-wse	no	—	inherited
clusterType · component property	enum	hosting \| fine-tuning	no	—	inherited
embeddingSyncMinutes · advanced	integer	—	no	—	inherited
inputs	enum	live \| historical \| both	no	live	▸ live
instances	integer	—	no	—	▸ 1
managed	boolean	—	no	false	▸ true
minimumCommitmentUnitHours · component property	integer	—	no	744	inherited
singleTenant · component property	boolean	—	no	true	inherited
snapshotToObjectStore · advanced	boolean	—	no	false	inherited
training	enum	batch \| online	no	batch	▸ batch
unitCount · component property	integer	—	no	1	inherited
unitShape · component property	string	—	no	H100_X1	inherited

Rules that apply · 1

Every rule whose selector covers this component's kind or its category. Whether a rule fires depends on the design: its properties, its edges and its groups.

Stateful node without zone redundancyerror

stateful-node-without-zone-redundancy

A stateful compute node pinned to exactly one availability zone disappears with that zone, and its state goes with it. Nodes inside a cell are exempt, because there the cell is deliberately single-zone and redundancy comes from the other cells.

— all of these hold:
— the node's `stateless` is false
— the node sits inside exactly 1 availability-zone group
— this does not hold:
— the node sits inside at least one cell group

Use it in a design

nodes:
  - { id: "generative-ai-cluster", component: "oci-generative-ai-cluster" }

Other ML inference products · 37

SageMaker endpointsagemaker-endpointawsml-inference Azure ML endpointazure-ml-endpointazureml-inference Workers AIcloudflare-workers-aicloudflareml-inference Anyscale Endpointsanyscale-endpointsml-inference Bananabanana-devml-inference Basetenbasetenml-inference Beambeam-cloudml-inference BentoMLbentomlml-inference Hugging Face Inference Endpointshuggingface-inferenceml-inference Infinityinfinity-embeddingsml-inference Janjanml-inference KServekserveml-inference llama.cpp serverllama-cpp-serverml-inference llm-dllm-dml-inference LM Studiolm-studioml-inference LMDeploylmdeployml-inference LocalAIlocalaiml-inference Generic ML inferenceml-inferenceml-inference MLC LLMmlc-llmml-inference Modalmodalml-inference Mystic AImystic-aiml-inference NVIDIA NIM (self-hosted)nvidia-nimml-inference OctoAIoctoaiml-inference Ollamaollamaml-inference Ray Serveray-serveml-inference Seldon Coreseldon-coreml-inference SGLangsglangml-inference TensorFlow Servingtensorflow-servingml-inference TensorRT-LLMtensorrt-llmml-inference Text Embeddings Inferencetext-embeddings-inferenceml-inference Text Generation Inferencetext-generation-inferenceml-inference TorchServetorchserveml-inference NVIDIA Tritontritonml-inference vLLMvllmml-inference Xinferencexinferenceml-inference Vertex AI endpointvertex-ai-endpointgcpml-inference OCI Data Science Model Deploymentoci-data-science-model-deploymentociml-inference

Source

1# yaml-language-server: $schema=../../schema/component.schema.json
2# Oracle OCI Generative AI dedicated AI cluster: single-tenant GPU capacity that hosts model
3# endpoints or runs fine-tuning. "Creating a Dedicated AI Cluster for Hosting Models": one unit
4# is created by default, each extra model replica needs another unit, unit shapes are named
5# instance type plus card count (H100_X1), and hosting a pretrained model commits 744 unit-hours.
6schemaVersion: "1"
7type: "component"
8id: "oci-generative-ai-cluster"
9kind: "ml-inference"
10provider: "oci"
11docs: "https://docs.oracle.com/en-us/iaas/Content/generative-ai/create-ai-cluster-hosting.htm"
12defaults:
13  accelerator: "gpu"
14  instances: 1
15  training: "batch"
16  inputs: "live"
17  managed: true
18properties:
19  clusterType:
20    type: "enum"
21    values: ["hosting", "fine-tuning"]
22  unitShape:
23    type: "string"
24    default: "H100_X1"
25  unitCount:
26    type: "integer"
27    default: 1
28  minimumCommitmentUnitHours:
29    type: "integer"
30    default: 744
31  singleTenant:
32    type: "boolean"
33    default: true

The same page as markdown, for an agent: /catalogue/components/oci-generative-ai-cluster.md