WebGPU and the Price of Compiling WGSL(hugodaniel.com)

38 points by todsacerdoti 1 year ago | 15 comments

How many GPUs is 1M/B/T tokens?(cedana.com)

14 points by kmavm 20 days ago | 4 comments

Cedana's interactive calculator that converts a token volume and model choice into an estimated number of GPUs (e.g., H100s) needed to serve it.

Gemma3 – The current strongest model that fits on a single GPU(ollama.com)

212 points by brylie 1 year ago | 86 comments

Show HN: Attaching to a virtual GPU over TCP(thundercompute.com)

308 points by bmodel 2 years ago | 104 comments

Intel D270 GPU AI Accelerator–Up to 480 GB LPDDR5X(intel.com)

293 points by hurricanepootis 13 days ago | 168 comments

Intel product page for its data center GPU D-series AI inference accelerators, including the D270 with up to 480 GB LPDDR5X memory.

FramePack – Enabling Fast Video Generation on Consumer GPUs(framepack.co)

15 points by zoudong376 1 year ago | 2 comments