sglang

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

MOSS-TTSD is a spoken dialogue generation model that enables expressive dialogue speech synthesis in both Chinese and English, supporting zero-shot multi-speaker voice cloning, and long-form speech generation.

LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU 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.

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

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

gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR、TTS、文生图、图片编辑和文生视频的开源框架。

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

A workload for deploying LLM inference services on Kubernetes

Arks is a cloud-native inference framework running on Kubernetes

A tool for benchmarking LLMs on Modal

A high-performance RDMA distributed storage system for fast LLM Inference and GPU Training

Make SGLang go brrr

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

Kernel Library Wheel for SGLang

A guide to structured generation using constrained decoding

Boosting GPU utilization for LLM serving via dynamic spatial-temporal prefill & decode orchestration

Controllable Language Model Interactions in TypeScript

Experiments with LLMs in clouds (powered by SGLang)