gekkom Follow 
Stars
Companion webpage to the book "Mathematics For Machine Learning"
A focused launcher for your desktop — native, fast, extensible
PyTorch building blocks for the OLMo ecosystem
Continuous Thought Machines, because thought takes time and reasoning is a process.
Modeling, training, eval, and inference code for OLMo
Fast and memory-efficient exact attention
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
A high performance Python permanent calculator implemented in C++
Code for the Fractured Entangled Representation Hypothesis position paper!
CUDA Python: Performance meets Productivity
An extremely fast Python package and project manager, written in Rust.
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Timelock Encryption made practical. The Go `tlock` library and the `tle` cmd line tool home to encrypt towards the future.
OpenUI let's you describe UI using your imagination, then see it rendered live.
Development repository for the Triton language and compiler
Unsloth Studio is a web UI for training and running open models like Qwen, DeepSeek, gpt-oss and Gemma locally.
LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progres…
NVIDIA Linux open GPU with P2P support
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Install and Run Python Applications in Isolated Environments
Windows-based client for Home Assistant. Provides notifications, quick actions, commands, sensors and more.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Deep and online learning with spiking neural networks in Python
Fluent theme for qBitTorrent