- CRITICAL: idle sweep now calls mark_stopped() after successful HTTP stop, preventing repeated stop POSTs on every 3rd tick for the same instance - CRITICAL: active_allocations() now filters by gpu_id to avoid marking wrong instance idle on multi-GPU nodes when an allocation is released - CRITICAL: VRAM pre-flight guard in ensure_service was dead code — added the actual HTTPException(503) before the candidate loop - IMPORTANT: register() now updates agent_url on re-registration if it changed, so relocated agents are tracked correctly - IMPORTANT: updated test_service_registry.py callers of active_allocations() to pass the now-required gpu_id argument |
||
|---|---|---|
| .. | ||
| config | ||
| db | ||
| llm | ||
| pipeline | ||
| resources | ||
| tasks | ||
| tiers | ||
| vision | ||
| wizard | ||
| __init__.py | ||