L

llama-cpp-power8

Project information

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. (Mirror of github.com/Scottcjn/llama-cpp-power8; full history archived 2026-10-20.)

36 Commits
3 Branches
1 Tag

README
Apache License 2.0
CONTRIBUTING

Created on

October 21, 2026

Loading