Starred repositories
Deformable ConvNets V2 (DCNv2) in PyTorch
Using OnnxRuntime to inference yolov10,yolov10+SAM ,yolov10+bytetrack , SAM2 and paddleOCR by c++ .
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
Serve, optimize and scale PyTorch models in production
NVIDIA GPU metrics exporter for Prometheus leveraging DCGM
Use Prometheus to monitor Kubernetes and applications running on Kubernetes
Kubebuilder - SDK for building Kubernetes APIs using CRDs
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"
Optimized primitives for collective multi-GPU communication
CUDA integration for Python, plus shiny features
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
DeepSeek LLM: Let there be answers
Train transformer language models with reinforcement learning.
A generative world for general-purpose robotics & embodied AI learning.
Universal LLM Deployment Engine with ML Compilation
OSI Layer 2 driver for nRF24L01 on Arduino & Raspberry Pi/Linux Devices
Low cost motion capture system for room scale tracking
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Unsupervised text tokenizer for Neural Network-based text generation.
♾️ CML - Continuous Machine Learning | CI/CD for ML