vec-inf 0.7.2__tar.gz → 0.7.3__tar.gz

{vec_inf-0.7.2 → vec_inf-0.7.3}/.github/workflows/docker.yml

@@ -21,7 +21,9 @@ on:
 jobs:
   push_to_registry:
     name: Push Docker image to Docker Hub
-    runs-on: ubuntu-latest
+    runs-on:
+      - self-hosted
+      - docker
     steps:
       - name: Checkout repository
         uses: actions/checkout@v5.0.0
@@ -32,6 +34,9 @@ jobs:
           VERSION=$(grep -A 1 'name = "vllm"' uv.lock | grep version | cut -d '"' -f 2)
           echo "version=$VERSION" >> $GITHUB_OUTPUT
 
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
       - name: Log in to Docker Hub
         uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef
         with:
@@ -40,7 +45,7 @@ jobs:
 
       - name: Extract metadata (tags, labels) for Docker
         id: meta
-        uses: docker/metadata-action@c1e51972afc2121e065aed6d45c65596fe445f3f
+        uses: docker/metadata-action@318604b99e75e41977312d83839a89be02ca4893
         with:
           images: vectorinstitute/vector-inference
 

{vec_inf-0.7.2 → vec_inf-0.7.3}/.pre-commit-config.yaml

@@ -17,7 +17,7 @@ repos:
     - id: check-toml
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.14.3'
+    rev: 'v0.14.5'
     hooks:
     - id: ruff
       args: [--fix, --exit-non-zero-on-fix]

{vec_inf-0.7.2 → vec_inf-0.7.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vec-inf
-Version: 0.7.2
+Version: 0.7.3
 Summary: Efficient LLM inference on Slurm clusters using vLLM.
 Author-email: Marshall Wang <marshall.wang@vectorinstitute.ai>
 License-Expression: MIT
@@ -30,7 +30,7 @@ Description-Content-Type: text/markdown
 [![code checks](https://github.com/VectorInstitute/vector-inference/actions/workflows/code_checks.yml/badge.svg)](https://github.com/VectorInstitute/vector-inference/actions/workflows/code_checks.yml)
 [![docs](https://github.com/VectorInstitute/vector-inference/actions/workflows/docs.yml/badge.svg)](https://github.com/VectorInstitute/vector-inference/actions/workflows/docs.yml)
 [![codecov](https://codecov.io/github/VectorInstitute/vector-inference/branch/main/graph/badge.svg?token=NI88QSIGAC)](https://app.codecov.io/github/VectorInstitute/vector-inference/tree/main)
-[![vLLM](https://img.shields.io/badge/vLLM-0.10.1.1-blue)](https://docs.vllm.ai/en/v0.10.1.1/)
+[![vLLM](https://img.shields.io/badge/vLLM-0.11.0-blue)](https://docs.vllm.ai/en/v0.11.0/)
 ![GitHub License](https://img.shields.io/github/license/VectorInstitute/vector-inference)
 
 This repository provides an easy-to-use solution to run inference servers on [Slurm](https://slurm.schedmd.com/overview.html)-managed computing clusters using [vLLM](https://docs.vllm.ai/en/latest/). **This package runs natively on the Vector Institute cluster environments**. To adapt to other environments, follow the instructions in [Installation](#installation).
@@ -43,7 +43,7 @@ If you are using the Vector cluster environment, and you don't need any customiz
 ```bash
 pip install vec-inf
 ```
-Otherwise, we recommend using the provided [`Dockerfile`](Dockerfile) to set up your own environment with the package. The latest image has `vLLM` version `0.10.1.1`.
+Otherwise, we recommend using the provided [`Dockerfile`](Dockerfile) to set up your own environment with the package. The latest image has `vLLM` version `0.11.0`.
 
 If you'd like to use `vec-inf` on your own Slurm cluster, you would need to update the configuration files, there are 3 ways to do it:
 * Clone the repository and update the `environment.yaml` and the `models.yaml` file in [`vec_inf/config`](vec_inf/config/), then install from source by running `pip install .`.
@@ -76,7 +76,7 @@ Models that are already supported by `vec-inf` would be launched using the cache
 #### Other commands
 
 * `batch-launch`: Launch multiple model inference servers at once, currently ONLY single node models supported,
-* `status`: Check the model status by providing its Slurm job ID.
+* `status`: Check the status of all `vec-inf` jobs, or a specific job by providing its job ID.
 * `metrics`: Streams performance metrics to the console.
 * `shutdown`: Shutdown a model by providing its Slurm job ID.
 * `list`: List all available model names, or view the default/cached configuration of a specific model.

{vec_inf-0.7.2 → vec_inf-0.7.3}/README.md

@@ -7,7 +7,7 @@
 [![code checks](https://github.com/VectorInstitute/vector-inference/actions/workflows/code_checks.yml/badge.svg)](https://github.com/VectorInstitute/vector-inference/actions/workflows/code_checks.yml)
 [![docs](https://github.com/VectorInstitute/vector-inference/actions/workflows/docs.yml/badge.svg)](https://github.com/VectorInstitute/vector-inference/actions/workflows/docs.yml)
 [![codecov](https://codecov.io/github/VectorInstitute/vector-inference/branch/main/graph/badge.svg?token=NI88QSIGAC)](https://app.codecov.io/github/VectorInstitute/vector-inference/tree/main)
-[![vLLM](https://img.shields.io/badge/vLLM-0.10.1.1-blue)](https://docs.vllm.ai/en/v0.10.1.1/)
+[![vLLM](https://img.shields.io/badge/vLLM-0.11.0-blue)](https://docs.vllm.ai/en/v0.11.0/)
 ![GitHub License](https://img.shields.io/github/license/VectorInstitute/vector-inference)
 
 This repository provides an easy-to-use solution to run inference servers on [Slurm](https://slurm.schedmd.com/overview.html)-managed computing clusters using [vLLM](https://docs.vllm.ai/en/latest/). **This package runs natively on the Vector Institute cluster environments**. To adapt to other environments, follow the instructions in [Installation](#installation).
@@ -20,7 +20,7 @@ If you are using the Vector cluster environment, and you don't need any customiz
 ```bash
 pip install vec-inf
 ```
-Otherwise, we recommend using the provided [`Dockerfile`](Dockerfile) to set up your own environment with the package. The latest image has `vLLM` version `0.10.1.1`.
+Otherwise, we recommend using the provided [`Dockerfile`](Dockerfile) to set up your own environment with the package. The latest image has `vLLM` version `0.11.0`.
 
 If you'd like to use `vec-inf` on your own Slurm cluster, you would need to update the configuration files, there are 3 ways to do it:
 * Clone the repository and update the `environment.yaml` and the `models.yaml` file in [`vec_inf/config`](vec_inf/config/), then install from source by running `pip install .`.
@@ -53,7 +53,7 @@ Models that are already supported by `vec-inf` would be launched using the cache
 #### Other commands
 
 * `batch-launch`: Launch multiple model inference servers at once, currently ONLY single node models supported,
-* `status`: Check the model status by providing its Slurm job ID.
+* `status`: Check the status of all `vec-inf` jobs, or a specific job by providing its job ID.
 * `metrics`: Streams performance metrics to the console.
 * `shutdown`: Shutdown a model by providing its Slurm job ID.
 * `list`: List all available model names, or view the default/cached configuration of a specific model.

{vec_inf-0.7.2 → vec_inf-0.7.3}/docs/index.md

@@ -12,7 +12,7 @@ If you are using the Vector cluster environment, and you don't need any customiz
 pip install vec-inf
 ```
 
-Otherwise, we recommend using the provided [`Dockerfile`](https://github.com/VectorInstitute/vector-inference/blob/main/Dockerfile) to set up your own environment with the package. The latest image has `vLLM` version `0.10.1.1`.
+Otherwise, we recommend using the provided [`Dockerfile`](https://github.com/VectorInstitute/vector-inference/blob/main/Dockerfile) to set up your own environment with the package. The latest image has `vLLM` version `0.11.0`.
 
 If you'd like to use `vec-inf` on your own Slurm cluster, you would need to update the configuration files, there are 3 ways to do it:
 * Clone the repository and update the `environment.yaml` and the `models.yaml` file in [`vec_inf/config`](https://github.com/VectorInstitute/vector-inference/blob/main/vec_inf/config), then install from source by running `pip install .`.

{vec_inf-0.7.2 → vec_inf-0.7.3}/docs/user_guide.md

@@ -149,35 +149,52 @@ Since batch launches use heterogeneous jobs, users can request different partiti
 
 ### `status` command
 
-You can check the inference server status by providing the Slurm job ID to the `status` command:
+You can check the status of all inference servers launched through `vec-inf` by running the `status` command:
+```bash
+vec-inf status
+```
+
+And you should see an output like this:
+```
+┏━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┓
+┃ Job ID    ┃ Model Name ┃ Status  ┃ Base URL              ┃
+┡━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━┩
+│ 1434429   │ Qwen3-8B   │ READY   │ http://gpu113:8080/v1 │
+│ 1434584   │ Qwen3-14B  │ READY   │ http://gpu053:8080/v1 │
+│ 1435035+0 │ Qwen3-32B  │ PENDING │ UNAVAILABLE           │
+│ 1435035+1 │ Qwen3-14B  │ PENDING │ UNAVAILABLE           │
+└───────────┴────────────┴─────────┴───────────────────────┘
+```
+
+If you want to check why a specific job is pending or failing, append the job ID to the status command:
 
 ```bash
-vec-inf status 15373800
+vec-inf status 1435035+1
 ```
 
 If the server is pending for resources, you should see an output like this:
 
 ```
-┏━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
-┃ Job Status     ┃ Value                      ┃
-┡━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
-│ Model Name     │ Meta-Llama-3.1-8B-Instruct │
-│ Model Status   │ PENDING                    │
-│ Pending Reason │ Resources                  │
-│ Base URL       │ UNAVAILABLE                │
-└────────────────┴────────────────────────────┘
+┏━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┓
+┃ Job Status     ┃ Value       ┃
+┡━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━┩
+│ Model Name     │ Qwen3-14B   │
+│ Model Status   │ PENDING     │
+│ Pending Reason │ Resources   │
+│ Base URL       │ UNAVAILABLE │
+└────────────────┴─────────────┘
 ```
 
 When the server is ready, you should see an output like this:
 
 ```
-┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
-┃ Job Status   ┃ Value                      ┃
-┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
-│ Model Name   │ Meta-Llama-3.1-8B-Instruct │
-│ Model Status │ READY                      │
-│ Base URL     │ http://gpu042:8080/v1      │
-└──────────────┴────────────────────────────┘
+┏━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┓
+┃ Job Status   ┃ Value                 ┃
+┡━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━┩
+│ Model Name   │ Qwen3-14B             │
+│ Model Status │ READY                 │
+│ Base URL     │ http://gpu105:8080/v1 │
+└──────────────┴───────────────────────┘
 ```
 
 There are 5 possible states:
@@ -190,7 +207,7 @@ There are 5 possible states:
 
 **Note**
 * The base URL is only available when model is in `READY` state.
-* For servers launched with `batch-launch`, the job ID should follow the format of "MAIN_JOB_ID+OFFSET" (e.g. 17480109+0, 17480109+1).
+* For servers launched with `batch-launch`, the job ID should follow the format of "MAIN_JOB_ID+OFFSET" (e.g. 1435035+0, 1435035+1).
 
 ### `metrics` command
 

{vec_inf-0.7.2 → vec_inf-0.7.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "vec-inf"
-version = "0.7.2"
+version = "0.7.3"
 description = "Efficient LLM inference on Slurm clusters using vLLM."
 readme = "README.md"
 authors = [{name = "Marshall Wang", email = "marshall.wang@vectorinstitute.ai"}]

{vec_inf-0.7.2 → vec_inf-0.7.3}/tests/vec_inf/cli/test_cli.py

@@ -135,7 +135,7 @@ def test_list_single_model(runner):
 
 
 def test_status_command(runner):
-    """Test status command."""
+    """Test status command with job ID argument."""
     with patch("vec_inf.cli._cli.VecInfClient") as mock_client_class:
         mock_client = MagicMock()
         mock_client_class.return_value = mock_client
@@ -154,6 +154,111 @@ def test_status_command(runner):
         assert "Meta-Llama-3.1-8B" in result.output
 
 
+def test_status_command_no_job_id_no_running_jobs(runner):
+    """Test status command with no argument when no jobs are running."""
+    with patch("vec_inf.cli._cli.VecInfClient") as mock_client_class:
+        mock_client = MagicMock()
+        mock_client_class.return_value = mock_client
+        mock_client.fetch_running_jobs.return_value = []
+
+        result = runner.invoke(cli, ["status"])
+
+        assert result.exit_code == 0
+        assert "No running jobs found." in result.output
+
+
+def test_status_command_no_job_id_single_running_job(runner):
+    """Test status command with no argument when one job is running."""
+    with patch("vec_inf.cli._cli.VecInfClient") as mock_client_class:
+        mock_client = MagicMock()
+        mock_client_class.return_value = mock_client
+        mock_client.fetch_running_jobs.return_value = ["12345"]
+
+        mock_status = MagicMock()
+        mock_status.model_name = "test-model-1"
+        mock_status.server_status = "READY"
+        mock_status.base_url = "http://localhost:8000"
+        mock_status.pending_reason = None
+        mock_status.failed_reason = None
+        mock_client.get_status.return_value = mock_status
+
+        result = runner.invoke(cli, ["status"])
+
+        assert result.exit_code == 0
+        assert "test-model-1" in result.output
+        mock_client.fetch_running_jobs.assert_called_once()
+        mock_client.get_status.assert_called_once_with("12345")
+
+
+def test_status_command_no_job_id_multiple_running_jobs(runner):
+    """Test status command with no argument when multiple jobs are running."""
+    with patch("vec_inf.cli._cli.VecInfClient") as mock_client_class:
+        mock_client = MagicMock()
+        mock_client_class.return_value = mock_client
+        mock_client.fetch_running_jobs.return_value = ["12345", "67890"]
+
+        mock_status_1 = MagicMock()
+        mock_status_1.model_name = "test-model-1"
+        mock_status_1.server_status = "READY"
+        mock_status_1.base_url = "http://localhost:8000"
+        mock_status_1.pending_reason = None
+        mock_status_1.failed_reason = None
+
+        mock_status_2 = MagicMock()
+        mock_status_2.model_name = "test-model-2"
+        mock_status_2.server_status = "PENDING"
+        mock_status_2.base_url = None
+        mock_status_2.pending_reason = "Waiting for resources"
+        mock_status_2.failed_reason = None
+
+        mock_client.get_status.side_effect = [mock_status_1, mock_status_2]
+
+        result = runner.invoke(cli, ["status"])
+
+        assert result.exit_code == 0
+        assert "test-model-1" in result.output
+        assert "test-model-2" in result.output
+        assert "12345" in result.output
+        assert "67890" in result.output
+        mock_client.fetch_running_jobs.assert_called_once()
+        assert mock_client.get_status.call_count == 2
+
+
+def test_status_command_no_job_id_multiple_jobs_json_mode(runner):
+    """Test status command with no argument and JSON mode for multiple jobs."""
+    with patch("vec_inf.cli._cli.VecInfClient") as mock_client_class:
+        mock_client = MagicMock()
+        mock_client_class.return_value = mock_client
+        mock_client.fetch_running_jobs.return_value = ["12345", "67890"]
+
+        mock_status_1 = MagicMock()
+        mock_status_1.model_name = "test-model-1"
+        mock_status_1.server_status = "READY"
+        mock_status_1.base_url = "http://localhost:8000"
+        mock_status_1.pending_reason = None
+        mock_status_1.failed_reason = None
+
+        mock_status_2 = MagicMock()
+        mock_status_2.model_name = "test-model-2"
+        mock_status_2.server_status = "FAILED"
+        mock_status_2.base_url = None
+        mock_status_2.pending_reason = None
+        mock_status_2.failed_reason = "Out of memory"
+
+        mock_client.get_status.side_effect = [mock_status_1, mock_status_2]
+
+        result = runner.invoke(cli, ["status", "--json-mode"])
+
+        assert result.exit_code == 0
+        output = json.loads(result.output)
+        assert isinstance(output, list)
+        assert len(output) == 2
+        assert output[0]["model_name"] == "test-model-1"
+        assert output[0]["model_status"] == "READY"
+        assert output[1]["model_name"] == "test-model-2"
+        assert output[1]["model_status"] == "FAILED"
+
+
 def test_shutdown_command(runner):
     """Test shutdown command."""
     with patch("vec_inf.cli._cli.VecInfClient") as mock_client_class:

{vec_inf-0.7.2 → vec_inf-0.7.3}/tests/vec_inf/cli/test_helper.py

@@ -10,6 +10,7 @@ from vec_inf.cli._helper import (
     BatchLaunchResponseFormatter,
     LaunchResponseFormatter,
     ListCmdDisplay,
+    ListStatusDisplay,
     MetricsResponseFormatter,
     StatusResponseFormatter,
 )
@@ -521,3 +522,251 @@ class TestListCmdDisplay:
         with patch.object(console, "print") as mock_print:
             display.display_all_models_output(model_infos)
             mock_print.assert_called_once()
+
+
+class TestListStatusDisplay:
+    """Test cases for ListStatusDisplay."""
+
+    def test_init(self):
+        """Test ListStatusDisplay initialization."""
+        job_ids = ["12345", "67890"]
+        statuses = [
+            StatusResponse(
+                model_name="test-model-1",
+                log_dir="/tmp/logs",
+                server_status="READY",
+                job_state="RUNNING",
+                raw_output="JobState=RUNNING",
+                base_url="http://localhost:8000",
+                pending_reason=None,
+                failed_reason=None,
+            ),
+            StatusResponse(
+                model_name="test-model-2",
+                log_dir="/tmp/logs",
+                server_status="PENDING",
+                job_state="PENDING",
+                raw_output="JobState=PENDING",
+                base_url=None,
+                pending_reason="Waiting for resources",
+                failed_reason=None,
+            ),
+        ]
+
+        display = ListStatusDisplay(job_ids, statuses, json_mode=False)
+
+        assert display.job_ids == job_ids
+        assert display.statuses == statuses
+        assert display.json_mode is False
+        assert isinstance(display.table, Table)
+
+    def test_init_json_mode(self):
+        """Test ListStatusDisplay initialization with JSON mode."""
+        job_ids = ["12345"]
+        statuses = [
+            StatusResponse(
+                model_name="test-model",
+                log_dir="/tmp/logs",
+                server_status="READY",
+                job_state="RUNNING",
+                raw_output="JobState=RUNNING",
+                base_url="http://localhost:8000",
+                pending_reason=None,
+                failed_reason=None,
+            )
+        ]
+
+        display = ListStatusDisplay(job_ids, statuses, json_mode=True)
+
+        assert display.json_mode is True
+
+    def test_display_multiple_status_output_table_mode(self):
+        """Test displaying multiple statuses in table mode."""
+        console = Console()
+        job_ids = ["12345", "67890"]
+        statuses = [
+            StatusResponse(
+                model_name="test-model-1",
+                log_dir="/tmp/logs",
+                server_status="READY",
+                job_state="RUNNING",
+                raw_output="JobState=RUNNING",
+                base_url="http://localhost:8000",
+                pending_reason=None,
+                failed_reason=None,
+            ),
+            StatusResponse(
+                model_name="test-model-2",
+                log_dir="/tmp/logs",
+                server_status="PENDING",
+                job_state="PENDING",
+                raw_output="JobState=PENDING",
+                base_url=None,
+                pending_reason="Waiting for resources",
+                failed_reason=None,
+            ),
+        ]
+
+        display = ListStatusDisplay(job_ids, statuses, json_mode=False)
+
+        with patch.object(console, "print") as mock_print:
+            display.display_multiple_status_output(console)
+            mock_print.assert_called_once()
+            # Verify the table was printed
+            assert mock_print.call_args[0][0] == display.table
+
+    def test_display_multiple_status_output_json_mode(self):
+        """Test displaying multiple statuses in JSON mode."""
+        console = Console()
+        job_ids = ["12345", "67890"]
+        statuses = [
+            StatusResponse(
+                model_name="test-model-1",
+                log_dir="/tmp/logs",
+                server_status="READY",
+                job_state="RUNNING",
+                raw_output="JobState=RUNNING",
+                base_url="http://localhost:8000",
+                pending_reason=None,
+                failed_reason=None,
+            ),
+            StatusResponse(
+                model_name="test-model-2",
+                log_dir="/tmp/logs",
+                server_status="FAILED",
+                job_state="FAILED",
+                raw_output="JobState=FAILED",
+                base_url=None,
+                pending_reason=None,
+                failed_reason="Out of memory",
+            ),
+        ]
+
+        display = ListStatusDisplay(job_ids, statuses, json_mode=True)
+
+        with patch("click.echo") as mock_echo:
+            display.display_multiple_status_output(console)
+            mock_echo.assert_called_once()
+
+            # Verify JSON output
+            output = mock_echo.call_args[0][0]
+            json_data = json.loads(output)
+            assert isinstance(json_data, list)
+            assert len(json_data) == 2
+            assert json_data[0]["model_name"] == "test-model-1"
+            assert json_data[0]["model_status"] == "READY"
+            assert json_data[0]["base_url"] == "http://localhost:8000"
+            assert json_data[1]["model_name"] == "test-model-2"
+            assert json_data[1]["model_status"] == "FAILED"
+            assert json_data[1]["base_url"] is None
+
+    def test_display_multiple_status_output_empty_list(self):
+        """Test displaying empty status list."""
+        console = Console()
+        job_ids = []
+        statuses = []
+
+        display = ListStatusDisplay(job_ids, statuses, json_mode=False)
+
+        with patch.object(console, "print") as mock_print:
+            display.display_multiple_status_output(console)
+            mock_print.assert_called_once()
+
+    def test_display_multiple_status_output_empty_list_json(self):
+        """Test displaying empty status list in JSON mode."""
+        console = Console()
+        job_ids = []
+        statuses = []
+
+        display = ListStatusDisplay(job_ids, statuses, json_mode=True)
+
+        with patch("click.echo") as mock_echo:
+            display.display_multiple_status_output(console)
+            mock_echo.assert_called_once()
+
+            output = mock_echo.call_args[0][0]
+            json_data = json.loads(output)
+            assert isinstance(json_data, list)
+            assert len(json_data) == 0
+
+    def test_display_multiple_status_output_single_status(self):
+        """Test displaying single status."""
+        console = Console()
+        job_ids = ["12345"]
+        statuses = [
+            StatusResponse(
+                model_name="single-model",
+                log_dir="/tmp/logs",
+                server_status="READY",
+                job_state="RUNNING",
+                raw_output="JobState=RUNNING",
+                base_url="http://localhost:8000",
+                pending_reason=None,
+                failed_reason=None,
+            )
+        ]
+
+        display = ListStatusDisplay(job_ids, statuses, json_mode=False)
+
+        with patch.object(console, "print") as mock_print:
+            display.display_multiple_status_output(console)
+            mock_print.assert_called_once()
+            # Verify table has one row
+            assert len(display.table.rows) == 1
+
+    def test_display_multiple_status_output_with_none_base_url(self):
+        """Test displaying statuses with None base_url."""
+        console = Console()
+        job_ids = ["12345"]
+        statuses = [
+            StatusResponse(
+                model_name="pending-model",
+                log_dir="/tmp/logs",
+                server_status="PENDING",
+                job_state="PENDING",
+                raw_output="JobState=PENDING",
+                base_url=None,
+                pending_reason="Resource allocation",
+                failed_reason=None,
+            )
+        ]
+
+        display = ListStatusDisplay(job_ids, statuses, json_mode=False)
+
+        with patch.object(console, "print") as mock_print:
+            display.display_multiple_status_output(console)
+            mock_print.assert_called_once()
+            # Verify the row was added (None base_url should be handled gracefully)
+            assert len(display.table.rows) == 1
+            # Verify table has correct number of columns
+            assert (
+                len(display.table.columns) == 4
+            )  # Job ID, Model Name, Status, Base URL
+
+    def test_display_multiple_status_output_json_with_none_values(self):
+        """Test JSON output with None values."""
+        console = Console()
+        job_ids = ["12345"]
+        statuses = [
+            StatusResponse(
+                model_name="pending-model",
+                log_dir="/tmp/logs",
+                server_status="PENDING",
+                job_state="PENDING",
+                raw_output="JobState=PENDING",
+                base_url=None,
+                pending_reason="Waiting",
+                failed_reason=None,
+            )
+        ]
+
+        display = ListStatusDisplay(job_ids, statuses, json_mode=True)
+
+        with patch("click.echo") as mock_echo:
+            display.display_multiple_status_output(console)
+            mock_echo.assert_called_once()
+
+            output = mock_echo.call_args[0][0]
+            json_data = json.loads(output)
+            assert json_data[0]["base_url"] is None
+            assert json_data[0]["model_status"] == "PENDING"