TPU

Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines

Announce Type: replace Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation. Using LoRA on a Google TPU v5p-8 for training and TPU v6e-8 (Trillium) for inference, we document the full set of code-level adaptations required to port a GPU-native training recipe - built on PyTorch, HuggingFace TRL, and FSDP - to the JAX +...

Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines

arXiv:2605.25645v2 Announce Type: replace Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation. Using LoRA on a Google TPU v5p-8 for training and TPU v6e-8 (Trillium) for inference, we document the full set of code-level adaptations required to port a GPU-native training recipe, built on PyTorch, HuggingFace TRL, and FSDP, to...

Google, Canonical team up to certify Ubuntu images for TPU VMs

Restartable Sequences

May 31st, 2026 @ justine's web page The best kept secret at the frontier of system programming right now is the Linux 4.18+ (c. 2018) concept of restartable sequences or rseq for short. They allow you to create thread-safe data structures without locks or atomics which scale to microprocessors with many cores. It's currently only possible to use rseq on Linux using handwritten assembly code.

Broadcom's custom ASIC biz adds South Korea's FuriosaAI to its empire

Magenta RealTime 2: Open and Local Live Music Models

We’re excited to share Magenta RealTime 2 (MRT2), a state-of-the-art open model and efficient real-time inference engine that enables you to build and play AI musical instruments on your laptop! To get started, download the apps on your MacBook (requires Apple Silicon). Unlike other large generative music models that work offline to turn a prompt into a track, MRT2 is a live, interactive model that you can control with MIDI and audio, in addition to text.

Gotta Grow Fast: Design and Benchmarking of a Tip Mount for High-Speed Vine Robots

arXiv:2606.06040v1 Announce Type: new Abstract: Soft, growing vine robots extend through tip eversion, a mechanism that enables navigation through cluttered environments. However, integrating cameras and other sensors at the tip is uniquely challenging because the material forming the tip is constantly renewed as the robot grows. This continual material turnover, combined with friction between internal layers, added tip weight, and fabric constriction, complicates sensor and tool mounting.

OpenAI's chief chip designer leaves in 16 months, joins Anthropic

OpenAI's Custom Chip program lead Clive Chan just announced his is leaving Sam Altman's company to join Anthropic. Chan joined OpenAI in January 2024. As per Chan's LinkedIn his designation at OpenAI was Member of Technical Staff and it is the same designation that he is joining Anthropic.

Google CEO called out 'biggest AI budget problem' of companies world over from IO stage with a solution

Google CEO Sundar Pichai shifted the AI conversation from to economics at this years’s Google I/O conference. Pichai warned that the companies around the world are blowing through their annual AI budgets by May due to runaway token usage. Pichai said the rapid rise of AI agents has created unprecedented costs for enterprises.

Why we're raising our price target on Broadcom despite its post-earnings sell-off

Broadcom posted strong quarterly results after the bell on Wednesday, but didn't provide enough upside to its guidance to move the stock higher. Revenue in the fiscal second quarter of 2026, which ended May 3rd, was $22.19 billion, a slight miss versus the $22.27 billion consensus forecast, according to estimates compiled by LSEG. On an annual basis, revenue rose 48%.