Add idle_stop_after_s to ServiceProfile (default 0 = never stop). Set 600s (10 min) timeout on vllm slot in all single-GPU profiles. Backward compatible; non-vllm services inherit default 0 (no auto-stop). |
||
|---|---|---|
| .. | ||
| test_resources | ||
| test_tasks | ||
| __init__.py | ||
| test_config.py | ||
| test_db.py | ||
| test_llm_router.py | ||
| test_stubs.py | ||
| test_tiers.py | ||