mirror of
https://github.com/ollama/ollama
synced 2026-04-23 08:45:14 +00:00
6aa7283076
The scheduler updates free VRAM based on current loaded models. This was mutating the persisted list of GPUs, and when coupled with the non-refreshing logic for Metal that lead to stale low VRAM reporting after unload. The fix is to make sure the GPU discovery always returns a copy so the schedulers GPU list is in fact ephemeral and doesn't leak any temporary adjustments back into the persistent list. |
||
|---|---|---|
| .. | ||
| cpu_linux.go | ||
| cpu_linux_test.go | ||
| cpu_windows.go | ||
| cpu_windows_test.go | ||
| gpu.go | ||
| gpu_darwin.go | ||
| gpu_info_darwin.h | ||
| gpu_info_darwin.m | ||
| runner.go | ||
| runner_test.go | ||
| types.go | ||