Improve code quality

examples/profiling-configs/rocprofv3_multi_gpu.json

@@ -12,7 +12,7 @@
     "nodes": 1,
     "gpus_per_node": 4,
     "time": "02:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": false
   },
 

examples/profiling-configs/rocprofv3_multi_node.json

@@ -12,7 +12,7 @@
     "nodes": 2,
     "gpus_per_node": 4,
     "time": "04:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": true
   },
 

examples/slurm-configs/README.md

@@ -379,7 +379,7 @@ madengine uses intelligent multi-layer configuration merging:
     "nodelist": "node01,node02",     // Optional: restrict job to these nodes (skips node health preflight)
     "gpus_per_node": 8,             // GPUs per node
     "time": "24:00:00",             // Wall time (HH:MM:SS)
-    "output_dir": "./slurm_output", // Local output directory
+    "output_dir": "./slurm_results", // Local output directory
     "results_dir": "/shared/results", // Shared results collection
     "shared_workspace": "/shared/workspace", // Shared workspace (NFS/Lustre)
     "exclusive": true,               // Exclusive node access
@@ -584,10 +584,10 @@ squeue -u $USER
 scontrol show job <job_id>
 
 # View output logs (real-time)
-tail -f slurm_output/madengine-*_<job_id>_*.out
+tail -f slurm_results/madengine-*_<job_id>_*.out
 
 # View error logs
-tail -f slurm_output/madengine-*_<job_id>_*.err
+tail -f slurm_results/madengine-*_<job_id>_*.err
 
 # Cancel job if needed
 scancel <job_id>
@@ -600,7 +600,7 @@ scancel <job_id>
 - Check SLURM partition exists: `sinfo`
 - Verify GPU resources available: `sinfo -o "%P %.5a %.10l %.6D %.6t %N %G"`
 - Check SLURM account/QoS settings
-- Review job script: `slurm_output/madengine_*.sh`
+- Review job script: `slurm_results/madengine_*.sh`
 
 ### Out of Memory Errors
 
@@ -715,8 +715,8 @@ MODEL_DIR=models/my-model madengine run \
 watch squeue -u $USER
 
 # 6. Check logs when complete
-ls -lh slurm_output/
-tail -f slurm_output/madengine-*_<job_id>_*.out
+ls -lh slurm_results/
+tail -f slurm_results/madengine-*_<job_id>_*.out
 ```
 
 ### vLLM Inference Workflow
@@ -739,7 +739,7 @@ MODEL_DIR=models/llama2-70b madengine run \
   --manifest-file build_manifest.json
 
 # 5. Monitor for OOM errors
-tail -f slurm_output/madengine-*_<job_id>_*.err | grep -i "memory"
+tail -f slurm_results/madengine-*_<job_id>_*.err | grep -i "memory"
 
 # 6. If OOM occurs, adjust config and rebuild
 # Edit your config file to set VLLM_KV_CACHE_SIZE to 0.6 or 0.7

examples/slurm-configs/basic/01-single-node-single-gpu.json

@@ -12,7 +12,7 @@
     "nodes": 1,
     "gpus_per_node": 1,
     "time": "01:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": false
   },
 

examples/slurm-configs/basic/02-single-node-multi-gpu.json

@@ -12,7 +12,7 @@
     "nodes": 1,
     "gpus_per_node": 8,
     "time": "12:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": true
   },
 

examples/slurm-configs/basic/03-multi-node-basic-nodelist.json

@@ -10,7 +10,7 @@
     "nodelist": "node01,node02",
     "gpus_per_node": 8,
     "time": "24:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": true,
     "network_interface": "eth0"
   },

examples/slurm-configs/basic/03-multi-node-basic.json

@@ -12,7 +12,7 @@
     "nodes": 2,
     "gpus_per_node": 8,
     "time": "24:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": true,
     "network_interface": "eth0"
   },

examples/slurm-configs/basic/04-multi-node-advanced.json

@@ -12,7 +12,7 @@
     "nodes": 4,
     "gpus_per_node": 8,
     "time": "48:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "results_dir": "/shared/results",
     "shared_workspace": "/shared/workspace",
     "exclusive": true,

examples/slurm-configs/basic/05-vllm-single-node.json

@@ -12,7 +12,7 @@
     "nodes": 1,
     "gpus_per_node": 4,
     "time": "02:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": true
   },
 

examples/slurm-configs/basic/06-vllm-multi-node.json

@@ -19,7 +19,7 @@
     "nodes": 2,
     "gpus_per_node": 4,
     "time": "00:45:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": true,
 
     "_comment_node_check": "Preflight GPU health check (helps avoid OOM from stale processes)",

examples/slurm-configs/basic/07-sglang-single-node.json

@@ -12,7 +12,7 @@
     "nodes": 1,
     "gpus_per_node": 4,
     "time": "02:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": true
   },
 

examples/slurm-configs/basic/08-sglang-multi-node.json

@@ -12,7 +12,7 @@
     "nodes": 2,
     "gpus_per_node": 4,
     "time": "04:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": true
   },
 

examples/slurm-configs/basic/cluster-amd-rccl.json

@@ -19,7 +19,7 @@
     "nodes": 1,
     "gpus_per_node": 8,
     "time": "12:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": true
   },
 

examples/slurm-configs/basic/sglang-disagg-custom-split.json

@@ -20,7 +20,7 @@
     "nodes": 7,
     "gpus_per_node": 8,
     "time": "04:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": true
   },
 

examples/slurm-configs/basic/sglang-disagg-multi-node.json

@@ -19,7 +19,7 @@
     "nodes": 5,
     "gpus_per_node": 8,
     "time": "04:00:00",
-    "output_dir": "./slurm_output",
+    "output_dir": "./slurm_results",
     "exclusive": true
   },
 

src/madengine/cli/utils.py

@@ -352,7 +352,6 @@ def display_performance_table(perf_csv_path: str = "perf.csv", session_start_row
             console.print("[yellow]⚠️  Performance CSV is empty[/yellow]")
             return
 
-        # Get session_start_row to mark current runs (don't filter, just mark)
         total_rows = len(df)
 
         # Try parameter first, then fall back to marker file
@@ -378,7 +377,7 @@ def display_performance_table(perf_csv_path: str = "perf.csv", session_start_row
         perf_table.add_column("Index", justify="right", style="dim")
         perf_table.add_column("Model", style="cyan")
         perf_table.add_column("Topology", justify="center", style="blue")
-        perf_table.add_column("Launcher", justify="center", style="magenta")  # Distributed launcher
+        perf_table.add_column("Launcher", justify="center", style="magenta")
         perf_table.add_column("Deployment", justify="center", style="cyan")
         perf_table.add_column("GPU Arch", style="yellow")
         perf_table.add_column("Performance", justify="right", style="green")
@@ -388,20 +387,23 @@ def display_performance_table(perf_csv_path: str = "perf.csv", session_start_row
         perf_table.add_column("Data Name", style="magenta")
         perf_table.add_column("Data Provider", style="magenta")        
 
-        # Helper function to format duration
+        # Helper function to format duration (accepts float seconds or "Xs" string)
         def format_duration(duration):
-            if pd.isna(duration) or duration == "":
+            if pd.isna(duration) or duration == "" or duration is None:
                 return "N/A"
             try:
-                dur = float(duration)
+                if isinstance(duration, str) and duration.strip().endswith("s"):
+                    dur = float(duration.strip()[:-1])
+                else:
+                    dur = float(duration)
                 if dur < 1:
                     return f"{dur*1000:.0f}ms"
                 elif dur < 60:
                     return f"{dur:.2f}s"
                 else:
                     return f"{dur/60:.1f}m"
             except (ValueError, TypeError):
-                return "N/A"
+                return str(duration) if duration else "N/A"
 
         # Helper function to format performance
         def format_performance(perf):