https://github.com/Entropic-Science/qr-sampler
qr-sampler
Plug any randomness source into LLM token sampling.

qr-sampler is an engine-agnostic framework that replaces standard pseudorandom token sampling with entropy from external sources — quantum random number generators (QRNGs), processor timing jitter, hardware noise, or any source you connect via gRPC or Python plugin. The core sampling pipeline has zero inference-engine dependencies; thin engine adapters integrate it with vLLM, vLLM-Metal, or any engine that supports logits processing.

pip install qr-sampler
Why qr-sampler?
Standard LLM inference uses pseudorandom number generators (PRNGs) for token sampling. PRNGs are deterministic — given the same seed, they produce the same output every time. qr-sampler replaces this with true randomness from physical processes:

Quantum RNGs — photon detectors, vacuum fluctuation devices, or any hardware QRNG over gRPC
Hardware noise — 63 thermal, timing, microarch, and GPU noise sources via OpenEntropy
Processor timing jitter — CPU clock variations as an entropy source (experimental)
Your own source — implement the EntropySource ABC or connect any hardware via the gRPC protocol
OS entropy — os.urandom() as a fallback or baseline
Consciousness-research context
qr-sampler provides infrastructure for studying whether conscious intent can influence quantum-random processes in LLM token selection. The signal amplification system converts thousands of random bytes into a single token choice, designed so that even a tiny statistical bias (e.g., 0.1% shift in byte means) produces a measurable effect on which token gets selected. All entropy is generated just-in-time — the quantum measurement happens after logits are computed, never before.

This is a research tool. It makes no claims about consciousness or quantum mechanics — it provides the infrastructure to run rigorous experiments.