Gemma 3 Inference: vLLM on GKE. Over 22k token/s (medium.com)

2 points by m4r1k 1y ago ↗ HN

0 comments

[ 2.2 ms ] story [ 10.9 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats