Hackernews posts about Jax
Jax is an open-source Python library developed by Google that provides automatic differentiation and XLA (Accelerated Linear Algebra) for efficient execution of machine learning models on CPUs and GPUs.
- Why Julia's GPU Accelerated Ode Solvers Are 20x-100x Faster Than Jax and PyTorch (www.stochasticlifestyle.com)
- First Looking into Jax (www.gilesthomas.com)
- Training a Simple World Model with Jax (www.alexinch.com)
- Fast Robot Kinematics and Dynamics in Jax (github.com)
- Jax Back Ends and Devices (www.gilesthomas.com)
- First Looking into Jax (www.gilesthomas.com)
- Speeding up MuJoCo 460x with Jax (www.alexinch.com)
- ZML: Between Jax and Llama.cpp (jaco-bro.github.io)
- How to Scale Your Model (jax-ml.github.io)
- Why Japanese companies do so many different things (davidoks.blog)
- Why Janet? (2023) (ianthehenry.com)
- The greatest shot in television: James Burke had one chance to nail this scene (2024) (www.openculture.com)
- Toshifumi Suzuki, founder of Seven-Eleven Japan, has died (www.referenceforbusiness.com)
- Getting arrested in Japan (sundaicity.com)
- Rust (and Slint) on a Jailbroken Kindle (sverre.me)
- ASCII by Jason Scott (ascii.textfiles.com)
- Jank now has its own custom IR (jank-lang.org)
- Naphtha shortages in Japan (www.nippon.com)
- Sonny Rollins, jazz saxophonist, has died (www.rollingstone.com)
- Japan’s robot wolf sells out as record bear attacks drive demand (www.independent.co.uk)