Welcome to LMDeploy’s tutorials!#
LMDeploy is a toolkit for compressing, deploying, and serving LLM.
LMDeploy has the following core features:
Efficient Inference: LMDeploy delivers up to 1.8x higher request throughput than vLLM, by introducing key features like persistent batch(a.k.a. continuous batching), blocked KV cache, dynamic split&fuse, tensor parallelism, high-performance CUDA kernels and so on.
Effective Quantization: LMDeploy supports weight-only and k/v quantization, and the 4-bit inference performance is 2.4x higher than FP16. The quantization quality has been confirmed via OpenCompass evaluation.
Effortless Distribution Server: Leveraging the request distribution service, LMDeploy facilitates an easy and efficient deployment of multi-model services across multiple machines and cards.
Interactive Inference Mode: By caching the k/v of attention during multi-round dialogue processes, the engine remembers dialogue history, thus avoiding repetitive processing of historical sessions.
Excellent Compatibility: LMDeploy supports KV Cache Quant, AWQ and Automatic Prefix Caching to be used simultaneously.
Documentation#
Get Started
Models
Large Language Models(LLMs) Deployment
Vision-Language Models(VLMs) Deployment
Quantization
Benchmark
Advanced Guide
API Reference