diff --git a/nemo_rl/models/generation/vllm/vllm_worker.py b/nemo_rl/models/generation/vllm/vllm_worker.py
index 55fc58f774..2237a9efde 100644
--- a/nemo_rl/models/generation/vllm/vllm_worker.py
+++ b/nemo_rl/models/generation/vllm/vllm_worker.py
@@ -539,7 +539,14 @@ def _get_raw_spec_counters(self) -> dict[str, float | list[float]]:
         """
         metrics: dict[str, float | list[float]] = {}
         if self.llm is not None:
-            for metric in self.llm.get_metrics():
+            if hasattr(self.llm, "get_metrics"):
+                vllm_prom_metrics = self.llm.get_metrics()
+            else:
+                # The AsyncLLM API does not implement get_metrics so we need to call the prometheus API ourselves
+                from vllm.v1.metrics.reader import get_metrics_snapshot
+
+                vllm_prom_metrics = get_metrics_snapshot()
+            for metric in vllm_prom_metrics:
                 if hasattr(metric, "values"):
                     metrics[metric.name] = metric.values
                 elif hasattr(metric, "value"):
diff --git a/tests/functional/grpo_non_colocated.sh b/tests/functional/grpo_non_colocated.sh
index c5fc5eb5dc..8c65aedda2 100755
--- a/tests/functional/grpo_non_colocated.sh
+++ b/tests/functional/grpo_non_colocated.sh
@@ -27,6 +27,7 @@ uv run coverage run -a --data-file=$PROJECT_ROOT/tests/.coverage --source=$PROJE
     policy.train_micro_batch_size=1 \
     policy.generation.colocated.enabled=false \
     policy.generation.colocated.resources.gpus_per_node=1 \
+    policy.generation.vllm_cfg.async_engine=true \
     cluster.gpus_per_node=2 \
     grpo.max_num_steps=2 \
     logger.tensorboard_enabled=true \