dusty-nv / NanoDBLinks
Zero-copy multimodal vector DB with CUDA and CLIP/SigLIP
☆56Updated 3 weeks ago
Alternatives and similar repositories for NanoDB
Users that are interested in NanoDB are comparing it to the libraries listed below
Sorting:
- CLIP and SigLIP models optimized with TensorRT with a Transformers-like API☆25Updated 8 months ago
- A collection of reference AI microservices and workflows for Jetson Platform Services☆39Updated 4 months ago
- A faster implementation of OpenCV-CUDA that uses OpenCV objects, and more!☆51Updated last week
- A utility library to help integrate Python applications with Metropolis Microservices for Jetson☆13Updated 5 months ago
- Pixel Parsing. A reproduction of OCR-free end-to-end document understanding models with open data☆21Updated 10 months ago
- Python scripts performing optical flow estimation using the NeuFlowV2 model in ONNX.☆47Updated 8 months ago
- Simple Implementation of TinyGPTV in super simple Zeta lego blocks☆15Updated 6 months ago
- A project that optimizes Whisper for low latency inference using NVIDIA TensorRT☆82Updated 7 months ago
- Converts CLIP models to ONNX☆11Updated 2 years ago
- EdgeSAM model for use with Autodistill.☆26Updated 11 months ago
- ☆110Updated 2 months ago
- EfficientSAM + YOLO World base model for use with Autodistill.☆10Updated last year
- Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX.☆54Updated last year
- Use Florence 2 to auto-label data for use in training fine-tuned object detection models.☆64Updated 9 months ago
- Simple CogVLM client script☆14Updated last year
- Model compression for ONNX☆96Updated 6 months ago
- Python scripts performing object detection using the YOLOv9 MIT model in ONNX.☆30Updated 8 months ago
- This repository provides optical character detection and recognition solution optimized on Nvidia devices.☆75Updated 3 weeks ago
- A tool convert TensorRT engine/plan to a fake onnx☆39Updated 2 years ago
- Evaluate the performance of computer vision models and prompts for zero-shot models (Grounding DINO, CLIP, BLIP, DINOv2, ImageBind, model…☆36Updated last year
- A reference example for integrating NanoOwl with Metropolis Microservices for Jetson☆30Updated 11 months ago
- Easy to use neural networks for NVIDIA Jetson (and desktop too!)☆73Updated 2 years ago
- Compare Savant and PyTorch performance☆13Updated last year
- JAX bindings for the flash-attention3 kernels☆11Updated 9 months ago
- ☆96Updated 8 months ago
- Optimized local inference for LLMs with HuggingFace-like APIs for quantization, vision/language models, multimodal agents, speech, vector…☆271Updated 7 months ago
- General Object Detection☆12Updated last year
- A component that allows you to annotate an image with points and boxes.☆21Updated last year
- Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.☆10Updated last year
- Which model is the best at object detection? Which is best for small or large objects? We compare the results in a handy leaderboard.☆70Updated last week