MTLResidencySet requestResidency postponement under cross-app pressure
Parent: Mac local LLMs: Memory and wired limits · Published reference · snapshot 2026-10-05
↓ Facts as markdownall context files
No source measures how often or how long Metal postpones a residency request when a second app holds GPU memory. The search for this concept returned only general sizing articles.
These notes link each claim to its source. A source may be a research report hosted on this site rather than the primary document. A published reference means the content is available; it does not certify independent review or accuracy.Read the editorial policy and follow the sources before relying on a claim.
Facts
- No source measures how often or how long Metal postpones a residency request when a second app holds GPU memory. The search for this concept returned only general sizing articles. [source]
- The concept is already covered by macos-memory-compressor-thrashing-from-gpu-visib.md, metal-residency-sets-and-llama-cpp-metal-internals.md and metal-mmap-span-mapping-and-residency-set-wiring.md; the batch-9 pass found no further primary source and no contradiction. [source]
Children
- No children recorded.