llm-serving

A high-throughput and memory-efficient inference and serving engine for LLMs

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

SGLang is a fast serving framework for large language models and vision language models.

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in performant way.

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 16+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Superduper: End-to-end framework for building custom AI applications and agents.

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Simple, scalable AI model deployment on GPU clusters

AICI: Prompts as (Wasm) Programs

MoBA: Mixture of Block Attention for Long-Context LLMs

RayLLM - LLMs on Ray (Archived). Read README for more info.

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

Community maintained hardware plugin for vLLM on Ascend

A highly optimized LLM inference acceleration engine for Llama and its variants.

A throughput-oriented high-performance serving framework for LLMs

A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine