Skip to content
#

ppc64le

Here are 116 public repositories matching this topic...

LLM infrastructure cost reduction via NUMA-aware weight banking: 147 t/s (8.8x stock llama.cpp) on refurbished enterprise POWER8. Self-hosted inference, no cloud APIs. Part of the Proof of Physical AI stack.

  • Updated Aug 29, 2026
  • Python

Add this topic to your repo

To associate your repository with the ppc64le topic, visit your repo's landing page and select "manage topics."

Learn more