SGLang is a high-performance serving framework for large language models and multimodal models.
Python 37.7k 9.8k
SGLang's TorchTPU Plugin
Python 64 12
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
Python 1.2k 374
High Performance Serving Runtime For Interactive Super Intelligence System
Python 1.6k 643
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Python 5.4k 941
JAX backend for SGL
Python 367 160
SGLang kernel library for Intel XPU
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
FlashMLA: Efficient Multi-head Latent Attention Kernels
