Minimalist ML framework for Rust

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.

Neural Networks for JAX

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…

Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

🦜🔗 Build context-aware reasoning applications

Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHX…

A playbook for systematically maximizing the performance of deep learning models.

TinyFive is a lightweight RISC-V emulator and assembler written in Python with neural network examples

A Python framework for performing information retrieval experiments, building on http://terrier.org/

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

A Python toolbox for performing gradient-free optimization

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry lead…

Inference Llama 2 in one file of pure 🔥

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

MLX: An array framework for Apple silicon

Collective communications library with various primitives for multi-machine training.

Drag & drop UI to build your customized LLM flow

Examples in the MLX framework

Accessible large language models via k-bit quantization for PyTorch.

LLM inference in C/C++

Differentiable probabilistic answer set programming

Simple, safe way to store and distribute tensors

CoreNet: A library for training deep neural networks

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.