Open-source local AI server configs, GFX906 runtime maintenance, reproducible benchmarks, and QC methods for affordable AI research infrastructure.
-
Updated
Jul 1, 2026 - Python
Open-source local AI server configs, GFX906 runtime maintenance, reproducible benchmarks, and QC methods for affordable AI research infrastructure.
Proof-carrying AI runtime with transactional token publication, exact resource admission, paged KV ownership, and verifiable provider evidence.
Exact local AI builds: devices, memory maps, measured limits, license checks and Y OS runbooks.
Auditable source/fallback/native performance benchmarks for the Rextio ecosystem
Reproducible CUDA AES benchmark suite for GPU AES modes, correctness checks, and raw benchmark artifacts.
Add a description, image, and links to the reproducible-benchmarks topic page so that developers can more easily learn about it.
To associate your repository with the reproducible-benchmarks topic, visit your repo's landing page and select "manage topics."