Cerin Amroth — ML, JWST & Security Research

Large models on smaller machines. Public telescope images, examined closely. Software claims, put to the test.

ML systems — large models, smaller machines

Loggetta Check your hardware, plan a training run, and keep the results. One install includes the runtime and kernels. v0.7.0 · Plan and run training · pip install loggetta → experts4bit-qlora Fine-tune and serve large MoE models on one GPU. Move weights to RAM or SSD when GPU memory runs out. v0.58.1 · Get started → grouped-nf4-gemm Compute directly on packed 4-bit weights. GPU kernels, memory tools, and tests you can reproduce. v0.51.0 · Get started → OpenVINO Upstream fixes keeping Intel-GPU LLM inference off the CPU-fallback path — three merged.

Latest ML research · 8 October 2026 · GitHub: Loggetta · PyPI · models · measured speed and architecture · lower-layer solution guides

Start with the problem

Problem	Route
I want to plan and run model training	Loggetta
My MoE still OOMs after `load_in_4bit=True`	experts4bit-qlora internals
I need to QLoRA-train fused MoE experts	experts4bit-qlora
My model is larger than GPU or host memory	e4b residency paths
Dequantizing every expert before GEMM is too slow	grouped-nf4-gemm
I need native MXFP4 or INT4 expert compute	grouped-nf4-gemm
I want to inspect the evidence methodology	Receipts-driven engineering

Astronomy — explore real JWST observations

Little red dots — an ongoing search Map published little red dots, explore an ongoing search of public JWST images, and follow individual sources through real telescope observations.

Security — find the flaw, help get it fixed

Vulnerability research Good-faith research & coordinated disclosure. Published disclosures ZisK zkVM: a soundness bug in signed remainder, fixed upstream. Vendor advisory GHSA-qjgg-fcj3-p9x3, rated Critical.

Contact: jordan@cerinamroth.com · security reports: security@cerinamroth.com · security.txt · consulting: jordananderson.work · Site data

Jordan Anderson’s public GPG key · Ed25519, expires 11 June 2028
Fingerprint: DAEF C03B 9188 793C 80E5 20C8 68F0 6663 C7FB 250F