2-5x faster 50% less memory local LLM finetuning

• Manual autograd engine - hand derived backprop steps.


• 2x to 5x faster than QLoRA. 50% less memory usage.


• All kernels written in OpenAI's Triton language.


• 0% loss in accuracy - no approximation methods - all exact.


• No change of hardware necessary. Supports NVIDIA GPUs since 2018+. Minimum CUDA Compute Cap

... See more

Mem0: The Memory Layer for Personalized AI

Mem0 provides a smart, self-improving memory layer for Large Language Models, enabling personalized AI experiences across applications.

Note: The Mem0 repository now also includes the Embedchain project. We continue to maintain and support Embedchain ❤️. You can find the Embedchain codebase in the embedchai

... See more

Super JSON Mode is a Python framework that enables the efficient creation of structured output from an LLM by breaking up a target schema into atomic components and then performing generations in parallel.

It supports both state of the art LLMs via OpenAI 's legacy completions API and open source LLMs such as via Hugging Face Transformers and vLLM .... See more