Lead story
Ask your AI
Top stories
Models & availability
Latest
← Feed
Copy✕ Close copy menu
Borrowing the Night: Reclaiming Idle Inference GPUs for Research
Runway built a capacity controller called deckard that reallocates GPUs between production inference and research based on daily demand cycles, using queueing theory to optimize allocations so that production tracks demand without over-provisioning and more GPUs are available for research overnight.
From the source
We built a lightweight capacity controller to do this reallocation (internally called deckard, after the Blade Runner protagonist who relentlessly reclaims replicants).
runway.com
Visit source ↗runway.com
- Announced
- 02 Jul 2026
- Detected
- 03 Sep 2026 14:37 UTC (+62d after)
