LMDeploy

Toolkit from InternLM for compressing, quantizing and serving LLMs with INT4/INT8 kernels on GPUs.

Visit Website

Introduction

Overview

LMDeploy integrates Patched-Triton back-end and web UI, delivering 10-15× speed-ups on InternLM and other models.

Key Capabilities

PTQ & AWQ quantization flows
Multi-GPU tensor & pipeline parallel
OpenAI-compatible FastAPI server

Back

Information

Websitelmdeploy.readthedocs.io
AuthorsInternLM Team
Published date2023/05/09

More Items

Ray

2017

RISELab (UC Berkeley), Anyscale Inc.

Ray is an open-source distributed compute engine that lets you scale Python and AI workloads—from data processing to model training and serving—without deep distributed-systems expertise.

ai-development ai-framework ai-train ai-serving

OpenVINO

2018

Intel

OpenVINO is an open-source toolkit from Intel that streamlines the optimization and deployment of AI inference models across a wide range of Intel® hardware.

ai-development ai-inference ai-serving

NVIDIA Dynamo

2025

NVIDIA

NVIDIA Dynamo is an open-source, high-throughput, low-latency inference framework that scales generative-AI and reasoning models across large, multi-node GPU clusters.

ai-development ai-inference ai-serving nvidia