Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.
JD.com's open-source high-performance LLM inference engine optimized for Chinese AI accelerators including Ascend NPU, Cambricon MLU, Moore Threads MUSA, and Iluvatar BI150. xLLM delivers 2.2x throughput over vLLM-Ascend on Qwen models through its service-engine decoupled architecture, full graph pipeline execution, global KV cache management, and dynamic MoE expert load balancing. Battle-tested in JD.com's production retail AI systems before open-source release.
ollama
The simplest way to run LLMs locally with 165K+ GitHub stars. One-command deployment, 100+ models, REST API, and multi-platform support.
ggml-org
Pure C/C++ LLM inference engine supporting CPUs, Apple Silicon, CUDA, and Vulkan
sgl-project
High-performance LLM and multimodal model serving framework with RadixAttention and structured generation.
mlc-ai
Universal LLM deployment engine using ML compilation for cloud, mobile, and web