RC

Scottcjn/ram-coffers

NUMA-distributed weight banking for LLM inference on IBM POWER8. 147 t/s (8.8x stock). Part of the Proof of Physical AI stack.

86 22 +0/wk
GitHub
ai-inference depin hebbian llama-cpp llm numa power8 powerpc proof-of-physical-ai vec-perm
Trend 0

Star & Fork Trend (12 data points)

Stars
Forks

Multi-Source Signals

Growth Velocity

Scottcjn/ram-coffers has +0 stars this period . Velocity data will be available after more historical data is collected.

Deep analysis is being generated for this repository.

Signal-backed technical analysis will be available soon.

Metric ram-coffers g4f-working efficient-transformers ollama-webui-traefik-docker
Stars 86 868686
Forks 22 127740
Weekly Growth +0 +0+0+0
Language C PythonPythonShell
Sources 1 111
License Apache-2.0 NOASSERTIONNOASSERTIONMIT

Capability Radar vs g4f-working

ram-coffers
g4f-working
Maintenance Activity 100

Last code push 0 days ago.

Community Engagement 100

Fork-to-star ratio: 25.6%. Active community forking and contributing.

Issue Burden 70

Issue data not yet available.

Growth Momentum 30

No measurable growth in the current period (first-day cold start expected).

License Clarity 95

Licensed under Apache-2.0. Permissive — safe for commercial use.

Risk scores are computed from real-time repository data. Higher scores indicate healthier metrics.