A research implementation for accelerating Large Language Model (LLM) inference through KV cache projection and selective recomputation. This project explores novel approaches to reduce Time-to-Fir…

A framework for few-shot evaluation of language models.

Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.

Hydragen: High-Throughput LLM Inference with Shared Prefixes

Simple wifi ground station running circuitpython

📡 Open Ground Station Network 🛰

breakout board for Semtech SX1280 LoRa radio compatible with RFM9x footprints

Simple wifi ground station running circuitpython

Library for SX12XX LoRa devices

CircuitPython driver for the Semtech SX1280 LoRa chip (2.4 GHz)

LoRa Mesh Network to relay messages and calculate distance between radios

A 2D arcade space shooter built using C# in the Unity Game Engine.

A small three question personality quiz built using JavaScript, CSS, HTML, the jQuery library, and the Bootstrap library.