Stars
Compiles Python to Rust, helping transition off of Python to Energy Efficient and Safe Rust Code
LM inference server implementation based on *.cpp.
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
Extend datasets with AI prompts. Module allows users to use GPT models on top of pandas dataframes. Simple solution for tasks such as text classification, sentiment analysis, NER, translation, etc.
A self-hosted BitTorrent indexer, DHT crawler, content classifier and torrent search engine with web UI, GraphQL API and Servarr stack integration.
Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.
parthdev99 / cake
Forked from evilsocket/cakeDistributed LLM and StableDiffusion inference for mobile, desktop and server.
Addition to the built-in Task Management plugin for authorization using CAS (Central Authentication Service)
A programming language with a simple no-keyword syntax for computing tensors and rational numbers with unlimited precision (NOTE: NewLang is experimental; see README)
class of simply math(don't working now(fully), but great idea)(now simple, before mb with teylor optimizations)
experimental branch of http://github.com/cuberite/cuberite with Forge support