vec-perm

Here are 2 public repositories matching this topic...

Scottcjn / ram-coffers

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 Sep 3, 2026
Python

Scottcjn / llama-cpp-power8

Star

llama.cpp optimizations for IBM POWER8: vec_perm non-bijunctive collapse, PSE hardware entropy, DCBT prefetch. Sovereign inference. Part of the Proof of Physical AI stack.

transformer ibm powerpc pse ppc64le power8 ai-inference llm llama-cpp llm-inference vintage-computing sovereign-ai vintage-hardware sovereign-inference proof-of-physical-ai vec-perm

Updated Aug 30, 2026
C

Add this topic to your repo

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

Learn more