guoqingbao/xinfer

Fast, flexible LLM inference

Pure Rust Inference Engine

Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2

a fast cross platform AI inference engine 🤖 using Rust 🦀 and WebGPU 🎮

Efficient AI Inference & Serving

A high-throughput and memory-efficient inference and serving engine for LLMs

fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

High-performance LLM, VLM, embedding, reranking, and audio inference for Apple Silicon and NVIDIA CUDA systems.

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.