Skip to content
#

tpus

Here are 9 public repositories matching this topic...

Language: All
Filter by language

Measurement harness for the sliding window attention premium in the vLLM TPU Ragged Paged Attention v3 kernel: per layer decode cost, block size control, throughput, and goodput for Gemma 4 31B on TPU v6e.

  • Updated Jul 29, 2026
  • Python

Improve this page

Add a description, image, and links to the tpus topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the tpus topic, visit your repo's landing page and select "manage topics."

Learn more