AI-Hypercomputer/JetStream
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
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 leading model flop utilization rates.
$ git clone https://github.com/google/paxml.gitJetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
▲ +112 ★ this week
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
▲ +9 ★ this week
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.
▲ +3 ★ this week
A simple, performant, and scalable Jax LLM!
▲ +3 ★ this week
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Data from GitHub · snapshot Nov 13, 2026