vLLM 上线 D3 决策模型：Jev Decision Index 双榜第一
vLLM 为 D3 全系六个模型合并 recipe，D3 在 Jev Decision Index 0.3.2 文本和视觉两榜均列第一，可通过 System One API 自托管做路由和打分。
Great work from @XunzhuoLiu and the vLLM Semantic Router team on D3. All six models, from 0.6B to 27B, now have merged vLLM recipes! D3 ranked #1 on both Jev Decision Index 0.3.2 boards: 66.3 text and 71.3 vision (Oct. 12 snapshot). Run multimodal decisions on your own infrastructure through /v1/systemone—with control over data residency, latency budgets and governance. vLLM serves decision models too: the full D3 family, Clef-Flash, Clef-Omni and Liquid d1, through the System One API. D3 returns choices, yes/no answers and scores with probabilities over text, JSON, images and videos. Useful for routing, classification and scoring without generating a long response. In the recipe benchmark, D3 27B delivers 1.8× the requests/sec of its checkpoint server on 1× MI325X at 64 concurrent clients, using the same mixed workload. Start with a current vLLM nightly: vllm serve vllm-sr/d3 Recipes for all six sizes: https://github.com/vllm-project/recipes/tree/main/models/vllm-sr API and supported models: https://docs.vllm.ai/en/latest/models/structured_decisions_models/
这条是引用着另一条写的：x.com/2008097400272084993/status/210920720728402…