Menu

Serving a stateful video world model on one RTX 4090: memory, flags and seeds in Hy-Nomas
📰

Serving a stateful video world model on one RTX 4090: memory, flags and seeds in Hy-Nomas

DEV Community: machinelearning·InferenceKey·7 days ago
#Pja0oWWh
Reading 0:00
15s threshold

Most open video models give you a clip and drop it. Hy-Nomas holds on to the world between calls, and that reshapes the server around it.

The model comes from Tencent Hunyuan, with weights and code under Apache-2.0 on the Hy-Nomas model card and in the Tencent-Hunyuan/Hy-Nomas repository . You steer it in 5-second turns, each built on the frames already made. The default launch shares one video between eight GPUs, but the authors also ship a low-memory preset for a lone RTX 4090. We tried it as published, on a 24 GB RTX 4090 on our cloud. Every figure below comes from the Hy-Nomas single-GPU research write-up .

Headline numbers: 88 to 94 seconds of GPU work per 5-second segment once warm (after the first call has loaded everything), an 18.5 GiB peak on the card, and a scene that stayed coherent for three turns.

The server is stateful, so plan in worlds

As it draws, the model writes notes on the scene and reads them before the next turn.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.