flyzenr's starred repositories
openmlsys-zh
《Machine Learning Systems: Design and Implementation》- Chinese Version
waymo-open-dataset
Waymo Open Dataset
Awesome-LLM-Inference
📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.
Lidar_AI_Solution
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, YUV2RGB, cuOSD,).
CUDA-Learn-Notes
🎉 Modern CUDA Learn Notes with PyTorch: fp32, fp16, bf16, fp8/int8, flash_attn, sgemm, sgemv, warp/block reduce, dot, elementwise, softmax, layernorm, rmsnorm.
argoverse-api
Official GitHub repository for Argoverse dataset
Awesome-Autonomous-Driving
awesome-autonomous-driving
TNT-Trajectory-Prediction
A Unofficial Pytorch Implementation of TNT: Target-driveN Trajectory Prediction
cuda-quantum
C++ and Python support for the CUDA Quantum programming model for heterogeneous quantum-classical workflows
FOST
FOST is a general forecasting tool, which demonstrate our experience and advanced technology in practical forecasting domains, including temporal, spatial-temporal and hierarchical forecasting. Current general forecasting tools (Gluon-TS by amazon, Prophet by facebook etc.) can not process and model structural graph data, especially in spatial domains, also those tools suffer from tradeoff between usability and accuracy. To address these challenges, we design and develop FOST and aims to empower engineers and data scientists to build high-accuracy and easy-usability forecasting tools.
CUDA-Optimization-Guide
Xiao's CUDA Optimization Guide [Active Adding New Contents]
Yolov5_Tensorrt_Win10
A simple implementation of tensorrt yolov5 python/c++🔥
TNT-VectorNet-and-HOME-Trajectory-Forecasting
Custom implementation of TNT-VectorNet and HOME architectures
tnt_vectornet_with_tensorrt
Vectornet with tensorrt deploy, less than 1ms/object for inference.
MMDeploy_Tutorials
Jupyter notebook tutorials for MMDeploy
DenseTNT_CARLA
A fork of DenseTNT