LLM server for inference

A reference table of the main LLM inference engines and servers along with their GitHub and documentation resources.

Less than 1 minute(122 words)simple

Quick Navigation

Difficulty: Intermediate
Estimated Time: 5-10 minutes
Prerequisites: basic LLM knowledge, familiarity with GPUs, Python environment, Docker basics

Here's the complete table with only the first and last columns in a single table:

Inference Engine/ServerResources
vLLMGitHub, Documentation
TensorRT-LLMGitHub, Documentation
Hugging Face Text Generation InferenceGitHub, Documentation
RayLLM with RayServeGitHub, Documentation
Triton Inference Server with TensorRT-LLMGitHub, Documentation
OllamaWebsite, GitHub
NVIDIA NIM (NeMo Inference Manager)Website, GitHub
llama.cppGitHub

This table provides the names of the inference engines/servers along with their respective resource links.