Daniel Hiltgen
Daniel Hiltgen
We haven't found a workaround, so for now recommend updating. Fixes #3916
The amdgpu drivers free VRAM reporting omits some other apps, so leverage the upstream DRM driver which keeps better tabs on things Marking draft until I can do more testing......
Carries (and obsoletes if we move this one forward first) #4266 and #4441 This refines our GPU discovery to split it into bootstrapping where we discover information about the GPUs...
This doesn't expose a UX yet, but wires the initial server portion of progress reporting during load TODO - [ ] Adjust waitUntilRunning to be smarter and look for stalled...
### What is the issue? When running model concurrency, the scheduler is unaware of WDDM KMD memory allocations on system memory and just looks like GPU reported memory usage, which...
This should help users isolate problems with their container runtime.
Wire up CI and build rigging to generate a unified Windows installer with x64 and arm64 payloads. At install time, the correct binaries will be installed for the platform. I...
Fixes #2549