Pinned Loading

1. sam3-tensorrt-optimization sam3-tensorrt-optimization Public

   Forked from facebookresearch/sam3

   5x faster, 3x smaller — TensorRT optimization pipeline for Meta SAM3 (40 FPS, split-module export, GPU preprocessing, mixed precision)

   Python

2. llm-compiler-optimizations llm-compiler-optimizations Public

   MLIR-based compiler optimizations for LLM inference — custom passes for attention, KV-cache, and memory scheduling on accelerator architectures

   MLIR 1

3. rf-detr-trt-opti rf-detr-trt-opti Public

   Forked from roboflow/rf-detr

   RF-DETR TensorRT optimization: 10x faster (753 FPS) with zero mAP loss. ONNX export, FP16 engine building, GPU preprocessing, and full COCO val2017 evaluation.

   Python 1

4. DG_Prune DG_Prune Public

   PyTorch DNN pruning library — unstructured and structured pruning with sparse-compute co-design for edge AI accelerators

   Python 1

5. Home-Vision-AI Home-Vision-AI Public

   Real-time multi-camera AI surveillance system with edge inference, object tracking, and event-driven alerts

   TypeScript

6. momorai momorai Public

   AI-powered personal assistant built in Go — lightweight, concurrent, and modular

   Go