A high-throughput and memory-efficient inference and serving engine for LLMs

Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.

An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

Everything you want to know about Google Cloud TPU

Run PyTorch in JAX. 🤝

JAX implementation of the Llama 2 model

JAX Synergistic Memory Inspector

Multiple dispatch over abstract array types in JAX.

Using JAX to generate piano music as MIDI

Configuration with Dataclasses+YAML+Argparse. Fork of Pyrallis