spb/localvm-research Public License
Running LLMs larger than memory on a consumer Mac — falsification-driven research: margin-gated deferred refinement, out-of-core verification on Apple Silicon. TR-01 published.
Python 63.2%
JavaScript 23.5%
CSS 11.8%
Shell 0.9%
Makefile 0.5%
1# =============================================================================2# Project : localvm-research3# File : experiments/micro/expE_partial_gemm/benchmark.py4# Purpose : Benchmark runner: Partial matrix multiplication: quality vs blocks evaluated, incl. a Metal kernel bandwidth check5# Author : Simon-Pierre Boucher6# Contact : contact@spboucher.ai7# Created : 2026-08-118# Modified : 2026-08-119# Platform : macOS / Apple Silicon (arm64)10# License : All rights reserved (research code)11# =============================================================================1213"""Benchmark entry point for expE_partial_gemm.1415Must embed the hardware manifest in all result output16(see benchmarks/hardware_manifest.py) and write results to17results/expE_partial_gemm/<timestamp>/.18"""1920import sys21from pathlib import Path2223sys.path.insert(0, str(Path(__file__).resolve().parents[3] / "benchmarks"))24from hardware_manifest import collect_manifest # noqa: E402252627def main() -> None:28 manifest = collect_manifest()29 raise NotImplementedError("experiment not yet implemented")303132if __name__ == "__main__":33 main()34