+
Skip to content
View WanRui37's full-sized avatar
  • Beijing Jiaotong University
  • Beijing

Block or report WanRui37

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
WanRui37/README.md

Hi 👋 I'm Wan Rui

I’m currently studying at Beijing Jiaotong University.

I'm diving deep into the intersection of hardware and AI, where the synergy between computational architecture and intelligent algorithms unlocks unprecedented efficiency and capabilities. Recently, I've been particularly drawn to the following areas:

  • 1) LLM inference acceleration: Optimizing LLM inference speed via quantization, kernel optimization, and parallel computing for high-throughput, low-latency deployment across hardware.
  • 2) Model high-performance optimization: Enhancing neural network efficiency end-to-end through algorithm adjustments (e.g., operator fusion) and hardware tuning, maximizing efficiency on resource-constrained devices.
  • 3) Binary Neural Networks (BNN): Developing 1-bit neural networks to reduce computation/memory usage while preserving performance, for energy-efficient AI systems.

📙 Skills

  • Python, C++, HLS, verilog, CUDA, Triton。

Pinned Loading

  1. galois galois Public

    Forked from galois-stack/galois

    a tensor computing compiler based tile programming for gpu, cpu or tpu

    C++

  2. galois-stack/galois galois-stack/galois Public

    a tensor computing compiler based tile programming for gpu, cpu or tpu

    C++ 46 15

  3. PaddlePaddle/FastDeploy PaddlePaddle/FastDeploy Public

    High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

    Python 3.5k 636

  4. FastDeploy FastDeploy Public

    Forked from PaddlePaddle/FastDeploy

    High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

    Python

点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载