Empowering everyone to build reliable and efficient software.

WilmerAI is one of the oldest LLM semantic routers. It uses multi-layer prompt routing and complex workflows to allow you to not only create practical chatbots, but to extend any kind of applicatio…

The core repository for Katanemo's advanced function calling models with top-tier performance. Features three collections: Arch-Function (core function calling), Arch-Function-Chat (conversational)…

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

Optimizing inference proxy for LLMs

Delivery infrastructure for agentic apps - Plano is an AI-native proxy and data plane that offloads plumbing work, so you stay focused on your agent's core logic (via any AI framework).

Thise repository hosts code for the global LLM challenge - a user study on human satisaction as it relates to LLM response quality

Cloud-native high-performance edge/middle/service proxy

🏙 Interactive performance profiling and debugging tool for PyTorch neural networks.

An open-source efficient deep learning framework/compiler, written in python.

Sokoban environment for OpenAI Gym

Summaries and notes on Deep Learning research papers

My Machine Learning blog