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）

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports 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 a performant way.

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

The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.

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

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

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

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

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

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

Community maintained hardware plugin for vLLM on Ascend

MoBA: Mixture of Block Attention for Long-Context LLMs

AICI: Prompts as (Wasm) Programs

Open Source Continuous Inference Benchmark Research Platform — Kimi K3 2.8T, MiniMax M3, DeepSeekv4, GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 & soon™ TPUv6e/v7/Trainium2/3 | 开源持续推理基准研究平台 — Kimi K2.7-Code、MiniMax M3、DeepSeekv4、GLM5 - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72，即将推出™ TPUv6e/v7/Trainium2/3

Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

A throughput-oriented high-performance serving framework for LLMs

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

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

♾️ Private Agent Fleet with Spec Coding. Each agent gets their own GPU-accelerated desktop. Run Claude, Codex, Gemini and open models on a full private AI Stack ♾️

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

LLM (Large Language Model) FineTuning