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

The best ChatGPT that $100 can buy.

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

Fast and accurate AI powered file content types detection

Common used path planning algorithms with animations.

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

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

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

yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.

Everything in Torch Fx

llm-export can export llm model to onnx.

A Toolkit to Help Optimize Onnx Model

A high-performance tool for video upscaling, interpolation, depth estimation, and more. Available as a CLI and Adobe Extension.

PyTorch implementation of AlphaZero Chess from scratch

A Toolkit to Help Optimize Large Onnx Model

🤗 Optimum ONNX: Export your model to ONNX and run inference with ONNX Runtime

Use safetensors with ONNX 🤗

caffe model to onnx

Machine Learning, Facial Rigger

Multi-stream video inference with Ultralytics YOLO - Display multiple video streams in a grid layout with real-time object detection.

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

tsingmicro AI model zoo