Scottcjn / ram-coffersView on GitHub
NUMA-distributed weight banking for LLM inference on IBM POWER8. 147 t/s (8.8x stock). Part of the Proof of Physical AI stack.
87Apr 8, 2026Updated last week

Alternatives and similar repositories for ram-coffers

Users that are interested in ram-coffers are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?