Give your team access to generative AI on infrastructure you control.
Using several AI models should not require someone to manage each machine by hand. Shared processing connects media requests from different workspaces to the hardware and models they need.
Applications share two GX10s through one coordinator, with model storage and results connected to the requesting workspace.
People request the media they need; the service handles model loading and placement, reusing loaded models and cached assets.
The GX10 pair supports media generation and paired DeepSeek serving. Media requests take priority; research serving returns after a period without media work.
1 / 3 · Shared AI on infrastructure you control
2 / 3 · Use multiple models without managing the machines
3 / 3 · Use the same hardware for different workloads
1 / 3 · Shared AI on infrastructure you control
Features
Multimedia requests
Submit supported speech, image, music, and video jobs with their reference files from your own workspace.
Model loading
Load the required models and reuse them where possible, with scheduling around available memory.
Shared scheduling
Queue work from multiple people and assign it to available hardware without each person managing the machines.
Recoverable delivery
Check output files and resume interrupted downloads into the workspace that submitted the request.
How it works
A coordinator queues multimedia jobs, loads the required models and collects their outputs. The same hardware can support background language-model serving between media workloads.