Who builds NVIDIA/TensorRT-LLM?

18 engineers on Vamo’s public Discover lists build NVIDIA/TensorRT-LLM, a Python repository with 15,079 stars on GitHub. The cards and the table below name each one, their role where their public card shows it, and what they did in the repo. To find every other contributor, run the search request further down or open the same search in Vamo.

Repository
NVIDIA/TensorRT-LLM
What it is
A library for defining Large Language Models and performing inference on NVIDIA GPUs.
Language
Python
Stars
15,079

Builders on the Discover lists

  • May
    Jul
    Aug
    Sep
    Oct
    Nov

    ML engineer on model pruning and int8 quantization in London

    Builds large language model pruning and quantization tooling from London. Contributes to openai/whisper, a speech recognition system, and ggml-org/llama.cpp, a library for large language model inference.

  • hijkzzz
    @hijkzzz
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    Research scientist on RL for LLMs at NVIDIA

    Ships research on reinforcement learning for large language models at NVIDIA. Creator of Awesome-LLM-Strawberry, a collection of LLM reasoning papers and resources, and contributes to OpenRLHF/OpenRLHF, a framework for reinforcement learning.

  • Gabriel Wu
    @lucifer1004
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    Polyglot engineer who ships GPU profiling tools at NVIDIA

    Maintains developer tooling for GPU profiling at NVIDIA. Creator of cp-wiki, a wiki for competitive programming notes, and VeloQ, a CLI for querying GPU profiles.

  • Iman Tabrizian
    @Tabrizian
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    Deep learning inference engineer shipping LLM optimization tooling at NVIDIA

    Builds tooling for efficient LLM inference on NVIDIA GPUs. Contributes to triton-inference-server/server, a server for cloud and edge inferencing, and pushes to triton-inference-server/tensorrtllm_backend, a TensorRT-LLM backend.

  • Zhenhua Wang
    @zhenhuaw-me
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    ML inference architect shipping LLM tooling for NVIDIA GPUs

    Builds libraries for efficient LLM inference on GPUs, after software engineering at Alibaba Group. Creator of tflite2onnx, a tool that converts TensorFlow Lite models to ONNX.

  • Joosung Yoon
    @eagle705
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    Solutions architect who still ships Korean NER models

    Ships LLM deployment architecture, after foundation model engineering at SK Telecom. Builds pytorch-bert-crf-ner, a named entity recognition model for Korean.

  • milesial
    @milesial
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    Deep learning engineer behind Pytorch-UNet, pushing LLM inference at NVIDIA

    Pushes inference performance for large language models, after deep learning algorithms work at NVIDIA. Commits to vllm-project/vllm, an engine for memory-efficient LLM inference, and maintains Pytorch-UNet, a library for image semantic segmentation.

  • Trevor Morris
    @trevor-m
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    ML runtime engineer building inference tooling on GPU stacks at NVIDIA

    Builds machine learning runtime infrastructure for compiled model inference, after software engineering at Amazon Web Services. Contributes to neo-ai/neo-ai-dlr, a runtime for machine learning models, and to neo-ai/tvm, a deep learning compiler stack.

  • Yan Bai
    @ISEEKYAN
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    RL post-training engineer shipping frameworks at NVIDIA

    Delivers reinforcement learning post-training frameworks at NVIDIA, after software engineering at ByteDance. Contributes to verl-project/verl, a framework for post-training reinforcement learning models.

  • RuQing Xu
    @xrq-phys
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    Linear algebra engineer shipping M1 BLAS kernels and CUDA fusion at NVIDIA

    Ships CUDA kernels and operator fusion for large model inference at NVIDIA. Creator of blis_apple, a BLIS fork with Apple M1 support, and maintains BliContractor.jl, a tensor contractor for Julia.

  • Tao Li @ NVIDIA
    @litaotju
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    Sr. software engineer optimizing LLM inference on NVIDIA GPUs with TensorRT

    Optimizes LLM inference on NVIDIA GPUs with TensorRT, after performance architecture at NVIDIA. Commits to NVIDIA/TensorRT-LLM, a library for defining and optimizing large language models, and triton-inference-server/tensorrtllm_backend, a backend for serving large language models.

  • Rundong Li
    @lirundong
    May
    Jul
    Aug
    Sep
    Oct
    Nov

    Hardware engineer with a quantization research streak at NVIDIA

    Works on hardware engineering at NVIDIA. Creator of shtthesis, an unofficial LaTeX thesis template for ShanghaiTech University, and quant-pack, a network quantization codebase.

NameGitHubRoleWork in this repo
Dorian Donaj MagasicDorijan10Contributes to NVIDIA/TensorRT-LLM.
hijkzzzhijkzzzSenior Research ScientistContributes to NVIDIA/TensorRT-LLM.
Gabriel Wulucifer1004Engineer Sr, Tech SWContributes to NVIDIA/TensorRT-LLM.
Iman TabrizianTabrizianSenior Deep Learning Software EngineerContributes to NVIDIA/TensorRT-LLM.
Zhenhua Wangzhenhuaw-meSenior ArchitectContributes to NVIDIA/TensorRT-LLM.
Joosung Yooneagle705LLM Solutions ArchitectContributes to NVIDIA/TensorRT-LLM.
milesialmilesialSenior Deep Learning Algorithms EngineerContributes to NVIDIA/TensorRT-LLM.
Trevor Morristrevor-mSenior Deep Learning Software EngineerContributes to NVIDIA/TensorRT-LLM.
Yan BaiISEEKYAN工程师Contributes to NVIDIA/TensorRT-LLM.
RuQing Xuxrq-physDeep Learning EngineerContributes to NVIDIA/TensorRT-LLM.
Tao Li @ NVIDIAlitaotjuSenior Software Engineer - TensorRTContributes to NVIDIA/TensorRT-LLM.
Rundong LilirundongHardware EngineerContributes to NVIDIA/TensorRT-LLM.
Yueh-Ting (eop) CheneopXDArchitect, SeniorContributes to NVIDIA/TensorRT-LLM.
Xiao SongXiaoSongXSSenior ArchitectContributes to NVIDIA/TensorRT-LLM.
Yifan YangYang-YiFanMember of Technical StaffContributes to NVIDIA/TensorRT-LLM.
Ruoqian GuoruoqianguoSoftware EngineerContributes to NVIDIA/TensorRT-LLM.
Huizi MaoRalphMaoMember of Technical StaffContributes to NVIDIA/TensorRT-LLM.
Yuxi ChicherichyAI Developer Technology EngineerContributes to NVIDIA/TensorRT-LLM.

The lists show a few people. This request to the developer search API returns everyone Vamo has seen contribute to the repository, ranked by devRank. It is the same search the app runs when you search for NVIDIA/TensorRT-LLM contributors in Vamo. The API docs cover every filter, and the repository index lists the other repos with builders on the lists.

POST /v2/developers/search
{  "repos": {    "names": [      "NVIDIA/TensorRT-LLM"    ],    "role": "contributor"  },  "filters": [    "And",    [      [        "is_bot",        "Eq",        false      ],      [        "is_org_account",        "Eq",        false      ]    ]  ],  "sort": "devrank"}
“Contributors to NVIDIA/TensorRT-LLM” as one request. The response lists each person and what matched.

Hire the people who build NVIDIA/TensorRT-LLM.