Fix zmq issue (#719)

Signed-off-by: Onur Yilmaz <oyilmaz@nvidia.com>
Signed-off-by: svcnemo-autobot <svcnemo-autobot@nvidia.com>
Co-authored-by: svcnemo-autobot <svcnemo-autobot@nvidia.com>

Author: oyilmaz-nvidia

.github/workflows/release.yaml

@@ -99,7 +99,7 @@ jobs:
       app-id: ${{ vars.BOT_ID }}
       skip-test-wheel: true
       wheel-content-ignore: "W002,W004,W009"
-      custom-container: nvcr.io/nvidia/pytorch:25.11-py3
+      custom-container: nvcr.io/nvidia/pytorch:26.06-py3
       no-build-isolation: true
       runner: ${{ needs.pre-flight.outputs.runner_prefix }}-gpu-x2-container
       container-options: "--gpus all --runtime=nvidia"

nemo_deploy/llm/inference/inference_base.py

@@ -15,6 +15,7 @@
 
 import atexit
 import logging
+import os
 from pathlib import Path
 from typing import List, Optional, Tuple, Union
 
@@ -521,10 +522,13 @@ def create_mcore_engine(
         materialize_only_last_token_logits=True,
     )
 
+    coordinator_host = os.environ.get("MASTER_ADDR")
+
     llm = MegatronLLM(
         model=model,
         tokenizer=tokenizer,
         inference_config=inference_config,
+        coordinator_host=coordinator_host,
     )
 
     # Wrap the engine to ensure cleanup