From the archive
Tuesday, 10 November
Folded from 23 sources that day.
Sorted by quality and by how many sources covered it, the same for everyone.
-
Optimizing Muse Spark Open on TPU v7 with SGLang-TorchTPU
Meta's 816B-parameter Muse Spark Open runs on one four-chip TPU v7 host using a megakernel for all 62 layers. It halves time per output token at low concurrency.
-
Pay for Hugging Face Hub with your Google Cloud Account
Hugging Face organizations can now link to a Google Cloud account via the Marketplace, so usage appears on the existing cloud bill. Only org admins can set it up, and subscriptions are reviewed before billing starts.