Skip to content
View iliailmer's full-sized avatar
💻
neovim (btw)
💻
neovim (btw)

Block or report iliailmer

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
iliailmer/README.md

Ilia Ilmer

ML systems, research software, and low-level implementations.

Machine Learning Engineer at Clio. I build applied ML systems and research software.

Previously at BILL. PhD in Computer Science from the CUNY Graduate Center.

Tools: Python, Rust, C/C++, PyTorch, LLM systems, AWS

Selected work

  • ParameterEstimation.jl — ODE parameter and initial-condition estimation; the main software output of my PhD.
  • tinyflow — flow matching from scratch in tinygrad.
  • llama-tinygrad — a minimal Llama 3.2 inference engine in tinygrad.
  • smol-autograd — a small C automatic-differentiation library with Adam.

Links

Website · LinkedIn · Google Scholar

Pinned Loading

  1. ParameterEstimation.jl ParameterEstimation.jl Public

    ParameterEstimation.jl is a Julia package for estimating parameters and initial conditions of ODE models given measurement data.

    MATLAB 31 8

  2. tinyflow tinyflow Public

    Flow Matching implemented in tinygrad

    Python 1

  3. llama-tinygrad llama-tinygrad Public

    tiny inference engine for llama 3.2

    Python

  4. smol-autograd smol-autograd Public

    trying to build a smol automatic differentiation library in the spirit of micrograd with adam optimizer

    C