[FPGA'26 Best Paper] KANELÉ: Kolmogorov–Arnold Networks for Efficient LUT-based Evaluation

Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

Historical Volkov Commander archives and source snapshots

Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

Implementation of all RL algorithms in a simpler way

Self-referential self-improving agents that can optimize for any computable task

[ECCV'24] Code for "Improving Medical Multi-modal Contrastive Learning with Expert Annotations"

playing with DDR DRAM bus fault injection

Official inference framework for 1-bit LLMs

A simple (300 lines of code) reproduction of Computational Life: How Well-formed, Self-replicating Programs Emerge from Simple Interaction

High-efficiency LLM inference engine in C++/CUDA. Run Llama 70B on RTX 3090.

Open-source CUDA, Triton and HIP compiler targeting multiple GPU and CPU architectures.

Tiny ASIC implementation for "The Era of 1-bit LLMs All Large Language Models are in 1.58 Bits" matrix multiplication unit

A 6502 based laptop design

A lightweight, lightning-fast, in-process vector database

Code for the 6502 microprocessor, mostly for the Replica 1 computer.

A LLM trained only on data from certain time periods to reduce modern bias

The best ChatGPT that $100 can buy.

Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage compu…

A contact solver for physics-based simulations involving 👚 shells, 🪵 solids and 🪢 rods.

Transparent Object Pose Estimation Using Differentiable Rendering evaluated on the Tracebot object canister

An python script implementation to solve classical Density Functional Theory for Lennard-Jones fluids on 1D and 3D geometries

Code. Music. Live.

Running TCP/IP over SWD lines

ESA's anomaly dataset of real satellite telemetry from three ESA missions

(ICLR 2025) TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling

A Python package for optimal 1D k-means clustering.

VQVAEs, GumbelSoftmaxes and friends

Сustom torch style machine learning framework with automatic differentiation implemented on numpy, allows build GANs, VAEs, etc.

Parameter-Free Optimizers for Pytorch