PyTorch-Based Fast and Efficient Processing for Various Machine Learning Applications with Diverse Sparsity
-
Updated
Aug 31, 2026 - Cuda
#
spconv
Here are 8 public repositories matching this topic...
Unofficial PyTorch implementation of the paper: "CenterNet3D: An Anchor free Object Detector for Autonomous Driving"
voxel lidar object-detection voxelnet sparse-convolution 3d-object-detection centernet centernet3d spconv
-
Updated
Aug 20, 2020 - Python
50%+ Faster Cylinder3D, compatible with current PyTorch, CUDA, and Spconv versions
-
Updated
Oct 28, 2024 - Python
Sparse ConvLSTM for Point Cloud Semantic Segmentation
-
Updated
Jun 8, 2021 - Python
spconv-Triton is a fast sparse convolution library with full operator support (SubM conv, Conv3D, Transposed Conv, Pooling). It is hardware-agnostic and runs on GPUs supporting Triton.
-
Updated
Jul 20, 2026 - Python
Sparse Autoencoder + Pruning for CMS jet classification | GSoC 2026 @ CERN-HSF | Built with spconv + PyTorch
deep-learning point-cloud pytorch autoencoder pruning high-energy-physics particle-physics model-compression sparse-neural-networks spconv gsoc2026 jet-classification
-
Updated
Mar 22, 2026 - Python
Prebuilt spconv v2.3.8 wheels for CUDA 12.8 / 13.0 with native Blackwell (RTX 50-series, sm_120) kernels — for default PyPI torch (cu130) or torch +cu128
cuda pytorch lidar wheels pointcloud b200 lidar-point-cloud 3dvision blackwell spconv b100 rtx-5090 rtx5080 blackwell-gpu rtx5060 blackwell-architecture rtx-pro-6000 gb200 rtx5070
-
Updated
Sep 2, 2026 - Shell
Add this topic to your repo
To associate your repository with the spconv topic, visit your repo's landing page and select "manage topics."