vLLM(@vllm_project):DiffusionGemma-Jev now runs on vLLM 🚀 Ask yes/no, multiple-choice, or scored questions and get confidence with every answer. vLLM seeds a canvas with the response template, leaves only the answer slots noisy, then reads a probability distribution from every slot in a single denoising step. Huge thanks to @mmastrac for driving this upstream! 🙏

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

36 Following 50.2K Followers

vLLM@vllm_project

2026.09.23 08:03

DiffusionGemma-Jev now runs on vLLM 🚀 Ask yes/no, multiple-choice, or scored questions and get confidence with every answer. vLLM seeds a canvas with the response template, leaves only the answer slots noisy, then reads a probability distribution from every slot in a single denoising step. Huge thanks to @mmastrac for driving this upstream! 🙏