SGLang is a high-performance serving framework for large language models and multimodal models.
Python 38.3k 10k
SGLang's TorchTPU Plugin
Python 70 22
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
Python 1.2k 380
High Performance Serving Runtime For Interactive Super Intelligence System
Python 1.6k 666
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Python 5.5k 949
JAX backend for SGL
Python 368 160
A workload for deploying LLM inference services on Kubernetes
SGLang kernel library for NPU
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
SGLang Kernel Wheel Index
SGLang kernel library for Intel XPU
