Skip to content
View StepfenShawn's full-sized avatar
🔥
Currently training model...
🔥
Currently training model...
237 followers · 11 following

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Pair ExtraordinaireAchievement: Starstruckx3Achievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Achievements

Achievement: QuickdrawAchievement: YOLOAchievement: Pair ExtraordinaireAchievement: Starstruckx3Achievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Highlights

Organizations

@llvm @Wechat-Group @TheAlgorithms @v-community @Cantonese-community

Block or report StepfenShawn

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.

Content in all repositories owned by your account will be closed.
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
StepfenShawn/README.md

  I'm Shawn, a SWE from China who started coding at 13 y.o.

I’m currently working full‑time as a robotics software engineer, focusing on robot perception and on‑device AI deployment. I also work remotely as a quantitative developer, optimizing low‑latency trading systems.

I wish RAM were cheaper 🙏🙏🙏 — Running LLMs on CPU and building Rust tooling would be much more fun if every gigabyte didn’t hurt my wallet.

Pinned Loading

  1. Cantonese Cantonese Public

    粤语編程語言.The Cantonese programming language.

    Rust 1.2k 48

  2. kota kota Public

    A lightweight, highly extensible ai code agent, built in Rust.

    Rust 100 12

  3. qwen_inference_in_rust qwen_inference_in_rust Public

    Runs the Qwen3.8 27B LLM on a single CPU with >=8GB of RAM, delivering up to ~7.4 tok/s. Written in pure Rust: no BLAS, no framework, no GPU!

    Rust 12 2

  4. ferrum_cloud ferrum_cloud Public

    Pure Rust implementation of Point Cloud Library (PCL).

    Rust 10 1

  5. ferris-grad ferris-grad Public

    A PyTorch-like autograd engine in under 1000 lines of Rust code.🦀

    Rust 9 1

  6. ShitCodify ShitCodify Public

    An AI-powered legacy code alchemist that carefully transforms clean code into shit code.

    TypeScript 135 3