GeForce RTX 3080 with CUDA capability sm_86 is not compatible with the current PyTorch installation. · Issue #45028 · pytorch/pytorch · GitHub
New compute capability: sm_37 - CUDA Programming and Performance - NVIDIA Developer Forums
Matching CUDA arch and CUDA gencode for various NVIDIA architectures - Arnon Shimoni
CUDA C++ Programming Guide
NVIDIA GPU Compute Capability解释_Forskamse的博客-CSDN博客
python - GPU Compute Capability 3.0 but the minimum required Cuda capability is 3.5 - Stack Overflow
Find the compute capability of your NVIDIA Graphics Card (GPU)
Drilling Down Into Nvidia's “Pascal” GPU
CUDA - Wikipedia
gpu - CUDA: What is the thread block limitation of devices whose compute capability is 1.0? - Stack Overflow
Xavier NX Compute Capability - Jetson Xavier NX - NVIDIA Developer Forums
CUDA Compatibility :: NVIDIA Data Center GPU Driver Documentation
CUDA Compute Capability 6.1 Features in OpenCL 2.0 - StreamHPC
CUDA Compatibility :: NVIDIA Data Center GPU Driver Documentation
Technical specifications of GPUs according to the compute capability. | Download Table
CUDA GPUs - Compute Capability | NVIDIA Developer
Find the compute capability of your NVIDIA Graphics Card (GPU)
Is the warp size always 32 in CUDA? | Nan Xiao's Blog
CUDA Compatibility :: NVIDIA Data Center GPU Driver Documentation
Diving Deep Into The Nvidia Ampere GPU Architecture
![GPU Computing] NVIDIA CUDA Compute Capability Comparative Table | Geeks3D](http://www.ozone3d.net/public/jegx/201006/gpucapsviewer_compute_capability.jpg "GPU Computing] NVIDIA CUDA Compute Capability Comparative Table | Geeks3D")