SGLang is a high-performance serving framework for large language models and multimodal models.
Python 38.4k 10.1k
SGLang's TorchTPU Plugin
Python 74 29
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
Python 1.3k 383
High Performance Serving Runtime For Interactive Super Intelligence System
Python 1.7k 687
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Python 5.5k 961
JAX backend for SGL
Python 374 161
SGLang kernel library for Intel XPU
SGLang Kernel Wheel Index
SGLang kernel library for NPU
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling