nvidia-nccl 2.18.3-1-1 source package in Ubuntu
Changelog
nvidia-nccl (2.18.3-1-1) unstable; urgency=medium * New upstream version 2.18.3-1 * Refresh existing patches. * Fix superfluous file pattern in d/copyright. * Add two new symbols. -- Mo Zhou <email address hidden> Wed, 19 Jul 2023 23:47:47 -0700
Upload details
- Uploaded by:
- Debian NVIDIA Maintainers
- Uploaded to:
- Sid
- Original maintainer:
- Debian NVIDIA Maintainers
- Architectures:
- amd64 arm64 ppc64el
- Section:
- misc
- Urgency:
- Medium Urgency
See full publishing history Publishing
Series | Published | Component | Section | |
---|---|---|---|---|
Mantic | release | multiverse | misc |
Downloads
File | Size | SHA-256 Checksum |
---|---|---|
nvidia-nccl_2.18.3-1-1.dsc | 2.1 KiB | 2d42751d2bee9e244057cf5d246c6627254778f4878ff27ebfa643dfb72b3af5 |
nvidia-nccl_2.18.3-1.orig.tar.gz | 354.1 KiB | b4f5d7d9eea2c12e32e7a06fe138b2cfc75969c6d5c473aa6f819a792db2fc96 |
nvidia-nccl_2.18.3-1-1.debian.tar.xz | 4.3 KiB | 2d7a9297f4dfddc8f609c5bc4e728d73e6da92b82ebf0ca4ccb4741982e3f703 |
Available diffs
- diff from 2.16.5-1-1 to 2.18.3-1-1 (184.6 KiB)
No changes file available.
Binary packages built by this source
- libnccl-dev: NVIDIA Optimized primitives for inter-GPU communication
NCCL (pronounced "Nickel") is a stand-alone library of standard communication
routines for GPUs, implementing all-reduce, all-gather, reduce, broadcast,
reduce-scatter, as well as any send/receive based communication pattern. It
has been optimized to achieve high bandwidth on platforms using PCIe, NVLink,
NVswitch, as well as networking using InfiniBand Verbs or TCP/IP sockets. NCCL
supports an arbitrary number of GPUs installed in a single node or across
multiple nodes, and can be used in either single- or multi-process (e.g., MPI)
applications.
.
This package contains the development files.
- libnccl2: NVIDIA Optimized primitives for inter-GPU communication
NCCL (pronounced "Nickel") is a stand-alone library of standard communication
routines for GPUs, implementing all-reduce, all-gather, reduce, broadcast,
reduce-scatter, as well as any send/receive based communication pattern. It
has been optimized to achieve high bandwidth on platforms using PCIe, NVLink,
NVswitch, as well as networking using InfiniBand Verbs or TCP/IP sockets. NCCL
supports an arbitrary number of GPUs installed in a single node or across
multiple nodes, and can be used in either single- or multi-process (e.g., MPI)
applications.
.
This package contains the shared objects.
- libnccl2-dbgsym: debug symbols for libnccl2