SGLang
High-performance serving framework for large language models and multimodal models.
Visit tool
sglang.io
About SGLang
SGLang is a high-performance serving framework for large language models and multimodal models. It is designed to be easy to install and deploy, and supports a wide range of open models and hardware platforms.
Description summarised by AI from the sources listed below.
Key features
- high-performance serving
- large language models
- multimodal models
- model & hardware flexibility
- day-0 support for various open models
- advanced optimizations
Use cases
- production-grade inference
- large-scale deployments
- reliable, low-latency, high-throughput serving
Pricing
Pricing model: Open source. Detailed plans are not recorded; check the official website for current prices.
Pricing from the tool's own website.
