The Large Model Systems Organization develops large models and systems that are open, accessible, and scalable.
Latest Blog
See all posts
SGLang Low-Latency Mode: Kernels and Runtime
Low-latency inference offers many opportunities for optimizations tailored to specific models, hardware and workloads. These optimizations often require extensive kernel fusion and duplicate code acro...
SGLang Powers Beam in Production
Reflection’s Beam is a 501B-parameter mixture-of-experts model with 23B active parameters per token, built for software engineering and long-horizon agentic tasks. With its planned Apache 2.0 release,...
SGLang and Miles Add Day-0 Support for Muse Spark Open
- Model: Muse Spark Open is an open-weight multimodal mixture-of-experts model. It uses an 816B-parameter text transformer backbone, with approximately 42 billion active parameters per token. It accep...
Projects
View all projects
Our Sponsors & Partners
Backed by leading companies and institutions advancing AI research.
Voltage Park, NVIDIA, Nebius, Google Cloud, AtlasCloud, a16z, AMD, InnoMatrix, Laude Institute, Hyperbolic, NovitaAI, Verda Cloud, Sky9, Kaggle, MBZUAI, Together, RunPod, Anyscale, HuggingFace