Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.

基于SparkTTS、OrpheusTTS等模型，提供高质量中文语音合成与声音克隆服务。

Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

☸️ Easy, advanced inference platform for large language models on Kubernetes. 🌟 Star to support our work!

OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)

gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR和TTS的开源框架。

kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.

Arks is a cloud-native inference framework running on Kubernetes

A tool for benchmarking LLMs on Modal

AI-based search done right

A guide to structured generation using constrained decoding

Kernel Library Wheel for SGLang

DeepSeek-V3, R1 671B on 8xH100 Throughput Benchmarks

Controllable Language Model Interactions in TypeScript

Experiments with LLMs in clouds (powered by SGLang)

The Private AI Setup Dream Guide for Demos automates the installation of the software needed for a local private AI setup, utilizing AI models (LLMs and diffusion models) for use cases such as general assistance, business ideas, coding, image generation, systems administration, marketing, planning, and more.

Reading notes on the open source code of AI infrastructure (sglang, llm, cutlass, hpc, etc.)

Bench360 is a modular benchmarking suite for local LLM deployments. It offers a full-stack, extensible pipeline to evaluate the latency, throughput, quality, and cost of LLM inference on consumer and enterprise GPUs. Bench360 supports flexible backends, tasks and scenarios, enabling fair and reproducible comparisons for researchers & practitioners.