SGLang Documentation — SGLang (original) (raw)

SGLang Documentation#

SGLang is a fast serving framework for large language models and vision language models. It makes your interaction with models faster and more controllable by co-designing the backend runtime and frontend language. The core features include:

• Fast Backend Runtime: Provides efficient serving with RadixAttention for prefix caching, zero-overhead CPU scheduler, prefill-decode disaggregation, speculative decoding, continuous batching, paged attention, tensor parallelism, pipeline parallelism, expert parallelism, structured outputs, chunked prefill, quantization (FP8/INT4/AWQ/GPTQ), and multi-lora batching.
• Flexible Frontend Language: Offers an intuitive interface for programming LLM applications, including chained generation calls, advanced prompting, control flow, multi-modal inputs, parallelism, and external interactions.
• Extensive Model Support: Supports a wide range of generative models (Llama, Gemma, Mistral, Qwen, DeepSeek, LLaVA, etc.), embedding models (e5-mistral, gte, mcdse) and reward models (Skywork), with easy extensibility for integrating new models.
• Active Community: SGLang is open-source and backed by an active community with industry adoption.

Advanced Features

• Speculative Decoding
• Structured Outputs
• Tool and Function Calling
• Reasoning Parser
• Structured Outputs For Reasoning Models
• Custom Chat Template
• Quantization
• LoRA Serving
• PD Disaggregation

References

• General Guidance
• Hardware Supports
• Multi-Node Deployment
• Performance Analysis & Optimization
• Developer Reference