Writing

    Field notes from an algorithm company.

    The thesis, the results, and the engineering discipline behind them — measured, cited, and reproduced across three serving stacks and two GPU vendors.

    Yantrion

    From algorithm to production performance.

    AI inference algorithms — 1.8–3.4× more resident capacity on the GPUs you already own.

    Our mission

    Writing kernels, solving hard problems, and a love of the math underneath — grateful that NVIDIA aligns with it.

    Member of the NVIDIA Inception Program

    © 2026 Yantrion, Inc. All rights reserved.

    Built at the metal — SGLang, vLLM & TensorRT-LLM.