Hugging Face Inference Endpoints

ML inferencehuggingface-inference

Managed deployment of a Hub model on dedicated autoscaling CPU or GPU replicas.

Provider: default
Kind: ML inference
Category: Compute
Official docs: https://huggingface.co/docs/inference-endpoints/en/guides/autoscaling
Also known as: Inference Providers

Properties · 4 set by this component

property	type	values	required	kind default	this component
accelerator	enum	none \| gpu \| asic	no	none	inherited
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
embeddingSyncMinutes · advanced	integer	—	no	—	inherited
inferenceEngine · component property	enum	tgi \| vllm \| custom-container	no	tgi	inherited
inputs	enum	live \| historical \| both	no	live	▸ live
instances	integer	—	no	—	inherited
managed	boolean	—	no	false	▸ true
pendingRequestsPerReplica · component property	boolean	—	no	false	inherited
scaleToZero · component property	boolean	—	no	false	inherited
scaleToZeroIdleMinutes · component property	integer	—	no	60	inherited
snapshotToObjectStore · advanced	boolean	—	no	false	▸ false
training	enum	batch \| online	no	batch	▸ batch
utilizationThresholdPercent · component property	integer	—	no	80	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: "huggingface-inference", component: "huggingface-inference" }

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 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 OCI Generative AI Dedicated AI Clusteroci-generative-ai-clusterociml-inference

Source

1# yaml-language-server: $schema=../../schema/component.schema.json
2# Hugging Face Inference Endpoints: managed service that deploys a Hub model on dedicated CPU or GPU
3# replicas behind a private endpoint. Per "Inference Endpoints" the infrastructure is fully managed and
4# replicas autoscale; per "Autoscaling", scale-to-zero idles the endpoint after 1 hour of inactivity,
5# utilisation scaling triggers at 80% CPU or GPU and at 1.5 pending requests per replica.
6schemaVersion: "1"
7type: "component"
8id: "huggingface-inference"
9kind: "ml-inference"
10provider: "default"
11docs: "https://huggingface.co/docs/inference-endpoints/en/guides/autoscaling"
12aliases: ["Inference Providers"]
13defaults:
14  managed: true
15  inputs: "live"
16  training: "batch"
17  snapshotToObjectStore: false
18properties:
19  scaleToZero:
20    type: "boolean"
21    default: false
22  scaleToZeroIdleMinutes:
23    type: "integer"
24    default: 60
25  utilizationThresholdPercent:
26    type: "integer"
27    default: 80
28  pendingRequestsPerReplica:
29    type: "boolean"
30    default: false
31  inferenceEngine:
32    type: "enum"
33    values: ["tgi", "vllm", "custom-container"]
34    default: "tgi"

The same page as markdown, for an agent: /catalogue/components/huggingface-inference.md