- 👋 Hi, I’m @Yashiru
- 🔧 ML performance engineer: from compilers, VM internals & Rust to making models run fast and cheap
- ⚡ Working with GPU programming (CUDA / Triton), PyTorch internals, and LLM inference (vLLM / SGLang)
- 💞️ I’m looking to collaborate on Rust, low-level performance, or ML inference projects
- 📫 How to reach me ?
🚀
ML performance engineering
Low level systems Engineer
-
@VeggiesLabs
- Geneva - Switzerland
-
05:38
(UTC +02:00) - @lgebor
Highlights
- Pro
Pinned Loading
-
rust-gpt
rust-gpt PublicA modern GPT trained from scratch on Rust source code, in PyTorch, with a from-scratch Rust BPE tokenizer.
Python
-
nn-forge
nn-forge PublicBuilding neural networks from scratch, from a character-level language model to a small Transformer.
Python
-
-
evm-rs-emulator
evm-rs-emulator PublicA blazingly fast in-memory Ethereum Virtual Machine (EVM) emulator written in Rust
-
huff-stack-comments
huff-stack-comments Public archiveA visual studio code extension that automatically generate the stack comments for Huff.
TypeScript 25
-
rust-bytecode-interpreter
rust-bytecode-interpreter Public archiveA very simple and experimental bytecode interpreter written in Rust
Rust
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.














