Starred repositories
🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools
A framework to compare low-bit integer and float-point formats
Fast and memory-efficient exact attention
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …
[CVPR 2025 Highlight] Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving
[CVPR 2023] Query-Centric Trajectory Prediction
[ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).
A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Simple samples for TensorRT programming
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
The devkit of the nuScenes dataset.
OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.
yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.
A parser, editor and profiler tool for ONNX models.
A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (p…
This is my translation of Chinese document of Eigen
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
YOLOv3、YOLOv4、YOLOv5、YOLOv5-Lite、YOLOv6-v1、YOLOv6-v2、YOLOv7、YOLOX、YOLOX-Lite、PP-YOLOE、PP-PicoDet-Plus、YOLO-Fastest v2、FastestDet、YOLOv5-SPD、TensorRT、NCNN、Tengine、OpenVINO
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
OpenMMLab Pose Estimation Toolbox and Benchmark.
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
deformable_conv2d layer implemented in pytorch