A Toolkit to Help Optimize Large Onnx Model

real time face swap and one-click video deepfake with only a single image

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

Verifile

Large Language Model Onnx Inference Framework

。

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

FlagGems is an operator library for large language models implemented in Triton Language.

Ultralytics YOLO11 🚀

[ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).

Detect CPU features with single-file

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

File consistency proofreader

llm deploy project based mnn.

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

llm-export can export llm model to onnx.

PyTorch implementation of AlphaZero Chess from scratch

A Toolkit to Help Optimize Large Onnx Model

Everything in Torch Fx

The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, WebAssembly

A easy tool for generating Tensor Program from Torch(besd on Torch FX & TVM Relax)

tsingmicro AI model zoo

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Common used path planning algorithms with animations.