[ buster ]
[ bullseye ]
[ bullseye-backports ]
[ bookworm ]
[ bookworm-updates ]
[ bookworm-backports ]
[ trixie ]
[ sid ]
[ experimental ]
[ Bron: nvidia-graphics-drivers ]
Pakket: nvidia-cuda-mps (545.23.06-4) [non-free]
Verwijzigingen voor nvidia-cuda-mps
Debian bronnen:
Het bronpakket nvidia-graphics-drivers downloaden:
- [nvidia-graphics-drivers_545.23.06-4.dsc]
- [nvidia-graphics-drivers_545.23.06.orig-amd64.tar.gz]
- [nvidia-graphics-drivers_545.23.06.orig-arm64.tar.gz]
- [nvidia-graphics-drivers_545.23.06.orig.tar.gz]
- [nvidia-graphics-drivers_545.23.06-4.debian.tar.xz]
Beheerders:
- Debian NVIDIA Maintainers (QA-pagina, Mailarchief)
- Andreas Beckmann (QA-pagina)
- Luca Boccassi (QA-pagina)
Externe bronnen:
- Homepage [www.nvidia.com]
Vergelijkbare pakketten:
Experimenteel pakket
Warning: This package is from the experimental distribution. That means it is likely unstable or buggy, and it may even cause data loss. Please be sure to consult the changelog and other possible documentation before using it.
NVIDIA CUDA Multi Process Service (MPS)
The Compute Unified Device Architecture (CUDA) enables NVIDIA graphics processing units (GPUs) to be used for massively parallel general purpose computation.
CUDA MPS is a feature that allows multiple CUDA processes to share a single GPU context. CUDA MPS should be transparent to CUDA programs.
CUDA MPS requires a device that supports Unified Virtual Address (UVA) and has compute capability SM 3.5 or higher. Pre-CUDA 4.0 APIs are not supported under CUDA MPS.
Andere aan nvidia-cuda-mps gerelateerde pakketten
|
|
|
|
-
- dep: libc6 (>= 2.34)
- GNU C Bibliotheek: Gedeelde bibliotheken
Ook een virtueel pakket geboden door: libc6-udeb