Huizi Mao (RalphMao): what they build

Huizi Mao (RalphMao) is a software engineer who works mostly in python, c++ and javascript. Deep learning optimization engineer at OpenAI Vamo shows Huizi Mao on the Engineers who build Nvidia's open-source AI software Discover list for their work on NVIDIA/TensorRT-LLM, read from what they have shipped on GitHub.

Huizi Mao and others on Engineers who build Nvidia's open-source AI software

  • Huizi Mao
    @RalphMao
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    Deep learning optimization engineer at OpenAI

    Compresses deep learning models for efficient inference, with research leadership from NVIDIA's deep learning team. Commits to NVIDIA/Model-Optimizer, a library that optimizes deep learning models.

  • May
    Jul
    Aug
    Sep
    Oct
    Nov

    Principal systems engineer who collects technical specs and builds C libraries

    Ships C and C++ systems tooling for CUDA developers, after principal engineering at OpenTeams. Creator of pdfs, a website that hosts a collection of technical PDFs, and perfecthash, a library that generates perfect hashes.

  • Eric Niebler
    @ericniebler
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    Distinguished C++ engineer behind the ranges that became std, ranges

    Develops C++ range and async execution libraries at NVIDIA, after software engineering at Meta. Creator of range-v3, a range library for C++, and works on NVIDIA/stdexec, a framework for asynchronous and parallel programming.

Vamo's read on Huizi Mao

devRank
86
Languages
python, c++, javascript

Compresses deep learning models for efficient inference, with research leadership from NVIDIA's deep learning team. Commits to NVIDIA/Model-Optimizer, a library that optimizes deep learning models.

The repos that put Huizi Mao on Vamo's lists

Discover lists Huizi Mao is on

Find engineers like Huizi Mao in Vamo, see RalphMao on GitHub, or browse every developer on Vamo's public lists.

Is this you? Email support@vamo.app and we will edit or take down this page.