C · Apache-2.0
Scottcjn/llama-cpp-power8
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.
★ 130
Stars
18 forks · 6 open issues
flat
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
17.8
Momentum / 100
see the breakdown below
10mo ago
Created
last push 42d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | flat, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 11.7 | last push 42d ago; decays to zero at 180 days |
| Scale | 15 | 6.1 | 130 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 17.8 | sum of the above |
Detail
| Topics | ai-inferenceibmllama-cppllmllm-inferencepower8powerpcppc64leproof-of-physical-aipsesovereign-aisovereign-inferencetransformervec-permvintage-computingvintage-hardware |
| Matched on | LLM & Inference (llm-inference) |
| Short window | +0 stars over 7 days = 0.0/day |
| Long window | no snapshot 14–45 days old yet |
| Lifetime average | 0.41 stars/day over 316 days |
| First seen here | 2026-10-29 |
| Last read | 2d ago |