Build, train, optimize, and run computer vision models locally, from raw images to live inference. Open source, optimized for Intel® XPU (CUDA also supported).
- openvino
- computer-vision
- deep-learning
- pytorch
111,821 visible repositories in the index
193–216 of 315 · Most stars
Build, train, optimize, and run computer vision models locally, from raw images to live inference. Open source, optimized for Intel® XPU (CUDA also supported).
pip install python-office 自动化办公专用库
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
Deploy a ML inference service on a budget in less than 10 lines of code.
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
Some Conferences' accepted paper lists (including AI, ML, Robotic)
A batched offline inference oriented version of segment-anything
OpenTelemetry Instrumentation for AI Observability
Offline inference engine for art, real-time voice conversations, LLM powered chatbots and automated workflows
The Prime Cross Site Request Forgery (CSRF) Audit and Exploitation Toolkit.
BAyesian Model-Building Interface (Bambi) in Python.
A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for 100+ DiTs.
https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.
Official Inference Code of EAGLE-4
The challenge projects for Inferencing machine learning models on iOS
Boxes.py - laser cutting boxes and more
wireless hacking - This is automated wireless hacking tool
Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
LLM KV cache compression made easy
Pytorch-Named-Entity-Recognition-with-BERT
Official inference code for SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory
Added vLLM support to IndexTTS for faster inference.