#sglang Repositories
Discover 38 active open source GitHub repositories tagged with #sglang, accumulating 109,680 total stars (averaging 2,886 stars per project). Leading this topic is xorbitsai/inference with 9,667 stars.
38 repositories total
Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.
Sharing AI Infra knowledge & code practice: PyTorch, vLLM/SGLang, slime/vime framework introduction โก๏ธ, performance acceleration ๐, large model basics ๐ง , AI software and hardware ๐ง, etc.
AI Fundamentals - GPU architecture, CUDA programming, basics of large models, and knowledge related to AI Agents.
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.
High-Performance Serving Runtime for Interactive Superintelligence Systems
A multilingual model for long-form, multi-speaker dialogue synthesis with flexible speaker control and zero-shot voice cloning
MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation Model
LLM model quantization (compression) toolkit with hardware acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU, Tenstorrent, Huawei Ascend NPU, and Intel/AMD/Apple CPUs via HF, vLLM, and SGLang.
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
A CLI to estimate inference memory requirements for Hugging Face models, written in Python.
Spark-x2.6 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models
Engine-agnostic LLM gateway in Rust. Full OpenAI and Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini, and more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant authentication.
Provides high-quality Chinese speech synthesis and voice cloning services based on models such as SparkTTS and OrpheusTTS.
sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Live support: https://discord.com/invite/GH5kRgv6ZD
Open Model Engine (OME) โ Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton
Frequently Asked Questions
What is the most popular #sglang repository on GitHub?
The top ranked open source #sglang project on GitHub is xorbitsai/inference with 9,667 stars. Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
Which programming languages are most used in #sglang repositories?
Among the top ranked #sglang projects on GitHub, the most common programming languages are Python, HTML, Rust, C++.
How is the #sglang repository ranking calculated?
We track 38 active open source repositories tagged with #sglang (500+ stars), totaling 109,680 stars with an average of 2,886 stars per repository. Rankings update daily from the GitHub API.