SGLang

Uses your system voice; voice and rate in settings.

Snapshot

≈ 1 min read

Names in other languages

No names in other languages are held for this entry yet.

Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.

SGLang (short for Structured Generation Language) is an open-source framework for programming and serving large language models and multimodal models. It was introduced by researchers affiliated with LMSYS and other institutions as a system combining a Python-embedded language for structured generation with a runtime for high-throughput inference. The project is designed for low latency and high-throughput inference workloads, and its documentation describes support for features such as structured outputs, speculative decoding, continuous batching, quantization, and compatibility with OpenAI-style APIs.

SGLang (short for Structured Generation Language) is an open-source framework for programming and serving large language models and multimodal models. It was introduced by researchers affiliated with LMSYS and other institutions as a system combining a Python-embedded language for structured generation with a runtime for high-throughput inference. The project is designed for low latency and high-throughput inference workloads, and its documentation describes support for features such as structured outputs, speculative decoding, continuous batching, quantization, and compatibility with OpenAI-style APIs.

Text derived from https://en.wikipedia.org/w/index.php?oldid=1371884452 under CC BY-SA 4.0; modifications have been made.

Sources cited in this revision

7 named source(s) extracted from the cited revision. A source with no author is shown by its publication; nothing is invented.