====
Blog
====

Deep dives into systems programming, GPU communication, and high-performance
computing topics beyond the typical cheatsheet format. These posts explore
real-world implementations, covering everything from RDMA networking and
GPUDirect to distributed training infrastructure. Each article walks through
the underlying architecture and provides practical insights for building
low-level, performance-critical systems.

.. toctree::
   :maxdepth: 1

   nvshmem