vh 894e92275d llama-swap: drop qwen3.6-35-a3b from pinned group — was blocking other model loads under memory pressure ...

Symptom: qwen3.6-35-a3b refused to deload when other models needed
the VRAM, even with the model itself at ttl: 0. The pinning came from
the `pinned` group's `persistent: true` flag, which exempts members
from eviction by the scheduler regardless of memory pressure. The
model's ttl: 0 only governs idle-timeout, NOT scheduler eviction —
those are separate concerns.

Removed qwen3.6-35-a3b from the group's members. Kept ttl: 0 on the
model itself: still no idle-unload, but the scheduler CAN now evict
it when another non-coexistent model is requested. qwen3.5-9b stays
pinned (~6 GB at Q4 — cheap to hold).

Updated the inline comment + the group-header docstring to reflect
the new semantics so future-Claude doesn't undo this.

2026-04-27 18:05:49 -07:00

..

config.yaml

llama-swap: drop qwen3.6-35-a3b from pinned group — was blocking other model loads under memory pressure

2026-04-27 18:05:49 -07:00