Add g6e.48xlarge

results.py

@@ -85,6 +85,13 @@ instance_type_mappings = {
         "url": "https://instances.vantage.sh/aws/ec2/g6e.12xlarge",
         "price": 5.2465,
     },
+    "g6e.48xlarge": {
+        "cloud": "AWS",
+        "gpu": "8xNVIDIA L40S",
+        "gpuRAM": "192 GB",
+        "url": "https://instances.vantage.sh/aws/ec2/g6e.48xlarge",
+        "price": 30.131,
+    },
     "g4dn.12xlarge": {
         "cloud": "AWS",
         "gpu": "4xNVIDIA T4",

results_virtuoso_large.py

@@ -3,5 +3,14 @@
 results_virtuoso_large = {
     "name": "Virtuoso-Large",
     "modelType": "Qwen2 72B",  # 2.5
-    "configurations": [],
+    "configurations": [
+        {
+            "instanceType": "g6e.48xlarge",
+            "quantization": "none",
+            "container": "LMI 0.30+vLLM 0.6.2",
+            "status": "OK",
+            "tokensPerSecond": "28",
+            "notes": "",
+        },
+    ],
 }

results_virtuoso_medium.py

@@ -44,6 +44,14 @@ results_virtuoso_medium = {
             "tokensPerSecond": "21",
             "notes": "--tensor-parallel-size 2 --max-model-len 16384",
         },
+        {
+            "instanceType": "g6e.48xlarge",
+            "quantization": "none",
+            "container": "LMI 0.30+vLLM 0.6.2",
+            "status": "OK",
+            "tokensPerSecond": "48",
+            "notes": "",
+        },
         {
             "instanceType": "p4d.24xlarge",
             "quantization": "none",

results_virtuoso_small.py

@@ -3,5 +3,14 @@
 results_virtuoso_small = {
     "name": "Virtuoso-Small",
     "modelType": "Qwen2.5 14B",
-    "configurations": [],
+    "configurations": [
+        {
+            "instanceType": "g6e.48xlarge",
+            "quantization": "none",
+            "container": "LMI 0.30+vLLM 0.6.2",
+            "status": "OK",
+            "tokensPerSecond": "78",
+            "notes": "",
+        },
+    ],
 }