vLLM(@vllm_project):Great work from @AMD and the vLLM Semantic Router team on d3-ultra! Open multimodal decision-making with per-answer probabilities, visual grounding, and video tracking—trained and served on AMD Instinct GPUs. Apache-2.0 weights on @huggingface.

vLLM

@vllm_project

A high-throughput and memory-efficient inference and serving engine for LLMs. Join to discuss together with the community!

Joined March 2024

37 Following 54.1K Followers

vLLM@vllm_project

2026.10.27 03:23

Great work from @AMD and the vLLM Semantic Router team on d3-ultra! Open multimodal decision-making with per-answer probabilities, visual grounding, and video tracking—trained and served on AMD Instinct GPUs. Apache-2.0 weights on @huggingface.

Xunzhuo@XunzhuoLiu

2026.10.27 03:01

Meet d3-ultra: our newest open 27B multimodal decision model. #2# of 230 on the Jev Decision Index text board, +3.03 over d3. Text, images, video: it boxes what it finds and tracks it through time. Open weights (Apache-2.0): #Jev# #Decision#