Hey Vested - what does this mean? Has something changed?

(almost) fully fused MLP layer from Llama!

An amazing overview of the core Rust types and traits: rustcurious.com/elements/

If you’ve been untangling next-gen GPU compute stacks like I have, this should be an interesting watch!

Fireworks passed ASIC speed! First time, GPU based inference crossed an ASIC provider. Benchmark credit to AA Model: GPT-OSS-120B Speed: 540 TPS Legend: Purple - Fireworks on B200; Orange - Groq

⚡️STMicroelectronics recently creating Rust drivers for their sensors and other components - One of the largest semiconductor companies in Europe, specializing in chips for automotive, industrial, and consumer electronics applications github.com/orgs/STMicroel…

New in-depth blog post time: "Inside NVIDIA GPUs: Anatomy of high performance matmul kernels". If you want to deeply understand how one writes state of the art matmul kernels in CUDA read along. (Remember matmul is the single most important operation that transformers execute