DirectoryInference runtimes › SGLang

SGLang

Inference runtimes ✓ verified 🔒 local-only Apache-2.0 30,212
GitHub ↗ Website ↗

SGLang is a fast serving framework for large language models and vision-language models. It provides efficient inference capabilities. The tool is designed to be self-hostable.

Who it's for: Developers and researchers who need to deploy and serve large language models and vision-language models should consider using SGLang.

Strengths

  • Fast serving framework
  • Supports LLMs and vision-language models
  • Self-hostable

Trade-offs

  • Limited information on its usage and deployment
  • No specific details on its performance or scalability

Data locality

Runs fully offline — no data leaves your machine.