Block a user
The broker can reclaim VRAM it did not allocate, but nothing stops a direct client taking it — a bare
ollama run still OOM-kills whisper
Broker must be the SOLE VRAM authority — close bypass gaps so out-of-band ollama holds get evicted (imagen starved by 24h keep-alive)
Partly closed — reclaim works, prevention does not
What now works, and is deployed on mRock:
Per-consumer residency comes from the GPU instead of from the consumers' own health responses,…