SGLang is a fast serving framework for large language models and vision language models.

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

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

Inference code for Llama models

Train very large language models in Jax.

seqax = sequence modeling + JAX

LoRA for arbitrary JAX models and functions

Minimal library to train LLMs on TPU in JAX with pjit().

Supercharge huggingface transformers with model parallelism.

DSPy: The framework for programming—not prompting—language models

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

🧱 Modula software package

Simple Transformer in Jax

Access large language models from the command-line

An implementation of the Llama architecture, to instruct and delight

Entropy Based Sampling and Parallel CoT Decoding

Open-source framework for the research and development of foundation models.