The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

Replay and track historical state

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

eRPC — fault-tolerant evm rpc proxy

A set of Helm charts to run multiple components of the Ethereum blockchain on Kubernetes.

Recipes for baking systemd-sysext images

🪢 Open source LLM engineering platform: Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

A cargo-subcommand to speed up Rust Docker builds using Docker layer caching.

Foundry is a blazing fast, portable and modular toolkit for Ethereum application development written in Rust.

Ethereum consensus client in Rust

This code sets up a simple yet robust server using FastAPI for handling asynchronous requests for embedding generation and reranking tasks using the BAAI M3 multilingual model.

🦜🔗 Build context-aware reasoning applications

Large Language Model Text Generation Inference

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

Build, cache, and run CLI tools scoped in Cargo.toml rather than installing globally. Stop the version drifts across your team, keep it all in sync within your project!