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

Better Harness Tools, not merely storing the archive of leaked Claude Code but also make shit things done. Now rewriting in Rust.

This project research aims to address the issue of overly long thinking chains in the Qwen3.5 model through data distillation-based fine-tuning. 本项目研究通过蒸馏数据对Qwen3.5模型的微调，解决Qwen3.5思维链思考过长的问题。

Nano vLLM with vLLM v1's request scheduling strategy and chunked prefill

A Flappy Bird Clone using python-pygame

First project for CVND: facial keypoint detection.

make images look like a cartoon image

PyTorch & CoreML implementation of MediaPipe Hands

ncnn is a high-performance neural network inference framework optimized for the mobile platform

ncnn android paddle ocr v5

Nano vLLM

PyTorch distributed training from scratch (for educational purposes only)

✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

Using pattern matcher in onnx model to match and replace subgraphs.

A web-based tool for transferring data between devices using QR codes, enabling offline file transfer without network connectivity. Built with Vue.js, pako, qrcode.js, and zbar-wasm.

paste image to markdown

BCC - Tools for BPF-based Linux IO analysis, networking, monitoring, and more

yolov8训练、剪枝、蒸馏、ncnn安卓部署全流程

本书为《C++17 the complete guide》的个人中文翻译，仅供学习和交流使用，侵删

A primitive library for neural network

Open standard for machine learning interoperability

Dynamic batching library for Deep Learning inference. Tutorials for LLM, GPT scenarios.

This repository contains tutorials and examples for Triton Inference Server

A Vim plugin to copy text through SSH with OSC52

An minimal Seq2Seq example of Automatic Speech Recognition (ASR) based on Transformer