Wafer pushes GLM-5.2 Fast onto AMD as Nvidia inference costs bite

The six-person inference startup says MI355X tuning got GLM-5.2 to 2626 tok/s/node, with Vercel and OpenRouter now carrying the model.

By · Published

Illustration of Wafer running GLM-5.2 Fast optimized on AMD MI355X hardware, with nods to Vercel and OpenRouter.

The six-person inference startup says MI355X tuning got GLM-5.2 to 2626 tok/s/node, with Vercel and OpenRouter now carrying the model.