SGLang
Open-source framework for large language model inference
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.
Nº Q139761223 ★★
Poco común · Literatura
SGLang
Open-source framework for large language model inference
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.
Último precio
—
Precio mínimo
—
Mediana 7 d
—
Ventas 30 d
0
Rango 30 d
—
En circulación
0
Cotización
mediana
mín – máx
ventas
Sin ventas en el periodo
Ver tabla
| Fecha | mediana | Mín | Máx | ventas |
|---|
Historial de ventas
- Última venta
- —
- Media 30 d
- —
- Mínimo 30 d
- —
- Máximo 30 d
- —
- Ventas 7 d
- 0
- Ventas 30 d
- 0
Aún no hay ventas.
Ventas anónimas: sin comprador ni vendedor. Las cifras solo cuentan ventas entre jugadores.
En Wikipedia
Texto en inglés Aún no hay artículo en tu idioma: extracto en inglés.
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.
Texto: Wikipedia en inglés, CC BY-SA 4.0. ·
