News for hackers. Stuff that matters.

A comment on Qwen-Image: Crafting with Native Text Rendering. Parent comment

Re:Qwen-Image: Crafting with Native Text Rendering by AuryGlenz on Tuesday August 05, 2025 @02:50AM (#44795018)
You can’t split image models over 2 GPUs like you can LLMs.
[ Parent | on HN ]
Re:Qwen-Image: Crafting with Native Text Rendering by 42lux on Tuesday August 05, 2025 @05:18AM (#44795919)
They also released an inference server for their models. Wan and qwen-image can be split without problems. https://github.com/modelscope/DiffSynth-Engine
[ Parent | on HN ]
Re:Qwen-Image: Crafting with Native Text Rendering by AuryGlenz on Wednesday August 06, 2025 @04:54PM (#44817719)
Unless I missed something just from skimming their tutorial it looks like they can do parallelism to speed things up with some models, not actually split the model (apart from the usual chunk offloading techniques).
[ Parent | on HN ]