vLLM Semantic Router releases d3-ultra, a 27B multimodal model
Original title: vLLM Semantic Router Releases d3-ultra: A 27B Open Multimodal Decision Model
The release is described as an open multimodal decision model; the article body was not available.
vLLM Semantic Router has released d3-ultra, described in the headline as a 27B open multimodal decision model. The captured page contained only a cookie-consent notice, so size, license, benchmarks, and availability details beyond the title are not in the text.
Unconfirmed: Only the headline was available; capabilities and release terms are not confirmed in the text.
- The model is named d3-ultra and is described as 27B.
- It is presented as open and multimodal.
- Organizations
- vLLM Semantic Router
- AI models
- d3-ultra
From the original article
14 min read at marktechpost.comvLLM Semantic Router released d3-ultra, a 27B open-weight multimodal decision model. It reads text, images and video once, then returns probabilities for every answer, scoring 87. 2 on the team’s SR-Text test.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.