[Feature] Add iteration level logging and enhance nvtx marker (#31193)

Signed-off-by: Max Hu <maxhu@nvidia.com>
Signed-off-by: Max Hu <hyoung2991@gmail.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>

vllm/config/observability.py

@@ -75,6 +75,12 @@ class ObservabilityConfig:
     enable_mfu_metrics: bool = False
     """Enable Model FLOPs Utilization (MFU) metrics."""
 
+    enable_logging_iteration_details: bool = False
+    """Enable detailed logging of iteration details.
+    If set, vllm EngineCore will log iteration details
+    This includes number of context/generation requests and tokens
+    and the elapsed cpu time for the iteration."""
+
     @cached_property
     def collect_model_forward_time(self) -> bool:
         """Whether to collect model forward time for the request."""