vLLM Watch posted an update
vLLM says its serving software delivered 1.3 billion tokens per dollar on SemiAnalysis AgentX while running DeepSeek-V4.1-Flash-1017.
Why it mattersThe project also cites 830,000 tokens per second per GPU, making a striking claim about the cost and speed of serving the model.
Discuss: When comparing inference systems, should cost per token matter more than peak throughput?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.