jakeloo
Follow
Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.
A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
Hyperlight is a lightweight Virtual Machine Manager (VMM) designed to be embedded within applications. It enables safe execution of untrusted code within micro virtual machines with very low latenc…
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
Database migrations. CLI and Golang library.
DSPy: The framework for programming—not prompting—language models
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation
Drag & drop UI to build your customized LLM flow
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Rust implementation of the Ethereum Virtual Machine.
Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Portable package manager for Neovim that runs everywhere Neovim runs. Easily install and manage LSP servers, DAP servers, linters, and formatters.
A symbolic execution engine for EVM smart contract binaries.
The simplest and most extensible zkVM. Fast and fully open source from a16z crypto and friends. ⚡
Extracts function selectors, arguments, state mutability and storage layout from EVM bytecode, even for unverified contracts
Sling is a CLI tool that extracts data from a source storage/database and loads it in a target storage/database.
The leading workflow orchestration platform. Run stateful step functions and AI workflows on serverless, servers, or the edge.