Daily AI news, sourcedWhere it stands
As of Oct 11, Decision 3.0 is a family of open multimodal decision models from the vLLM Semantic Router team that take text or JSON plus optional images and return Choice, Yes/No, or Score probabilities in one call without generating text.
- Official
vLLM Semantic Router releases Decision 3.0, five Apache-2.0 multimodal decision models from 0.8B to 27B
Hugging Face vllm-sr/d3 published this on Oct 11, 2026 (source: huggingface.co).
Decision 3.0 is a family of open multimodal decision models from the vLLM Semantic Router team that take text or JSON plus optional images and return Choice, Yes/No, or Score probabilities in one call without generating text. The five sizes are d3-lite (0.85B), d3-nano (2.21B), d3-mini (4.54B), d3-flash (8.39B), and d3 (26.09B), fine-tuned from Qwen3.5/Qwen3.8 bases with vision encoders; the team reports d3 leading its internal text (64.1) and vision (71.6) Decision Index 0.3.1 tables, with median text latency from about 22 ms to 84 ms on one AMD Instinct MI325X.
Source: Hugging Face vllm-sr/d3
- Official
- An institution announces something that has already happened, through its own channel or a founder or executive account.
- Statement by …
- A named person's views, predictions, plans or comments, including remarks reported by media when the original is unavailable.
- Reported by …
- Only media or another third party is saying it. We name the outlet.
- Unconfirmed
- Circulating online (posts, comments, leaks). No company, named person or outlet has confirmed it.
Items older than 72 hours never go in Top stories and show their original date.