mirror of
https://github.com/ollama/ollama.git
synced 2025-04-01 16:38:50 +02:00
9929751cc8
Until ROCm v6.2 ships, we wont be able to get accurate free memory reporting on windows, which makes automatic concurrency too risky. Users can still opt-in but will need to pay attention to model sizes otherwise they may thrash/page VRAM or cause OOM crashes. All other platforms and GPUs have accurate VRAM reporting wired up now, so we can turn on concurrency by default.