Skip to content
View triple-mu's full-sized avatar
💭
Contributing for the open source community.
💭
Contributing for the open source community.
410 followers · 15 following

Achievements

Achievement: Pair Extraordinairex4Achievement: Starstruckx3Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pair Extraordinairex4Achievement: Starstruckx3Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Block or report triple-mu

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
triple-mu/README.md

Typing SVG

github follow github follow Email 知乎 bilibili

📊 GitHub Stats & Productive Time

Stats Productive Time

👋 Nice to meet you！

Let me give a brief introduction!

This is triple-mu, 🤣 a fix typo programmer based in Beijing, China.

I am participating in mmyolo yolov6 yolov7 yolort projects as a co-author.

You can reach me in the following ways:

QQ: 3394101

Email: gpu@163.com

My usual programming languages

python cplusplus cuda java html JavaScript cmake

My usual programming tools

pycharm clion jupyter git github github-actions vscode latex visualstudio

My project is based on

pytorch oneflow numpy macOS linux ubuntu windows redmi

Popular repositories Loading

  1. YOLOv8-TensorRT YOLOv8-TensorRT Public

    YOLOv8 using TensorRT accelerate !

    Python 1.8k 301

  2. ncnn-examples ncnn-examples Public

    Learning ncnn with some examples

    Python 74 11

  3. TensorRT2ONNX TensorRT2ONNX Public

    A tool convert TensorRT engine/plan to a fake onnx

    Python 41 5

  4. fast-ulysses fast-ulysses Public

    Ulysses sequence-parallel all-to-all as a torch custom op, moved by the GPU copy engines over NVSHMEM symmetric memory. Zero SM usage; 1.7-2.2x over torch.distributed on NVLink.

    Python 32 4

  5. yolov8 yolov8 Public

    Forked from ultralytics/ultralytics

    YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite

    Python 21 7

  6. Qwen-Image-TensorRT Qwen-Image-TensorRT Public

    Qwen-Image's DiT inference with TensorRT-10

    Python 21 2