admin dec534cc88 Trial GPU-resident Qwen3.5-9B with verified 4B rollback

2026-10-27 17:14:38 +01:00

..

install-llama-cpp.sh

Sync workstation helpers and preserve baseline deployment

2026-09-09 13:31:47 +02:00

install-signal-cli.sh

Initial commit

2026-09-05 22:47:35 +02:00

llama_watchdog.py

Make local inference limits and workstation setup reproducible

2026-10-23 13:27:50 +02:00

prepare-workstation.py

Trial GPU-resident Qwen3.5-9B with verified 4B rollback

2026-10-27 17:14:38 +01:00