Code here:

Llama 4 inference in pure JAX! Expert/tensor parallelism with int8 quantization. Contributions welcome!

RT @froystig: A nice and concise R1 inference jax:tpu port by @rdyro128523. Good for both reading and running. Watch the repo for more.

Link to repo:

Deepseek R1 inference in pure JAX! Currently on TPU, with GPU and distilled models in-progress. Features MLA-style attention, expert/tensor parallelism & int8 quantization. Contributions welcome!

RT @cgarciae88: The JAX team is hosting a dinner / networking event during NVIDIA's GTC in March. Join us for an evening of food, drinks, a….

RT @jacobaustin132: Making LLMs run efficiently can feel scary, but scaling isn’t magic, it’s math! We wanted to demystify the “systems vie….

RT @sharadvikram: We now have a guide to writing distributed communication on TPU using Pallas, written by @JustinFu769512! .