SGLang is a high-performance serving framework for large language models and multimodal models.
Python 39k 10.6k
SGLang's TorchTPU Plugin
Python 86 55
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
Python 1.3k 397
High Performance Serving Runtime For Interactive Super Intelligence System
Python 1.8k 764
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Python 5.6k 992
JAX backend for SGL
Python 381 165
A workload for deploying LLM inference services on Kubernetes
SGLang kernel library for NPU
SGLang kernel library for Intel XPU
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling