MLC LLM

Compiler-based LLM engine for CUDA, ROCm, Metal and Vulkan with an OpenAI-compatible REST server.

Provider: default
Kind: ML inference
Category: Compute
Official docs: https://llm.mlc.ai/docs/deploy/rest.html

Properties · 4 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
device · component property	enum	auto \| cuda \| rocm \| metal \| vulkan \| opencl	no	auto	inherited
embeddingSyncMinutes · advanced	integer	—	no	—	inherited
inputs	enum	live \| historical \| both	no	live	▸ live
instances	integer	—	no	—	inherited
managed	boolean	—	no	false	▸ false
mode · component property	enum	local \| interactive \| server	no	local	inherited
port · component property	integer	—	no	8000	inherited
snapshotToObjectStore · advanced	boolean	—	no	false	inherited
training	enum	batch \| online	no	batch	▸ batch

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: "mlc-llm", component: "mlc-llm" }

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 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# MLC LLM: machine-learning compiler and engine that runs LLMs on CUDA, ROCm, Metal, Vulkan and OpenCL devices, with an
3# OpenAI-compatible REST server. Per "REST API", `mlc_llm serve` listens on 127.0.0.1:8000 in "local" mode (low
4# concurrency, batch size 4); "interactive" serves one request at a time and "server" maximises concurrency.
5schemaVersion: "1"
6type: "component"
7id: "mlc-llm"
8kind: "ml-inference"
9provider: "default"
10docs: "https://llm.mlc.ai/docs/deploy/rest.html"
11defaults:
12  training: "batch"
13  inputs: "live"
14  accelerator: "gpu"
15  managed: false
16properties:
17  port:
18    type: "integer"
19    default: 8000
20  mode:
21    type: "enum"
22    values: ["local", "interactive", "server"]
23    default: "local"
24  device:
25    type: "enum"
26    values: ["auto", "cuda", "rocm", "metal", "vulkan", "opencl"]
27    default: "auto"

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