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. Some citations identify archived research reports that are no longer hosted on this site. 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.