SuperNova g6e.2xlarge

results_arcee_supernova.py

@@ -28,6 +28,14 @@ results_arcee_supernova = {
             "tokensPerSecond": "33",
             "notes": "MAX_INPUT_TOKENS: 8192, MAX_TOTAL_TOKENS: 16384",
         },
+        {
+            "instanceType": "g6e.2xlarge",
+            "quantization": "awq (w4 g128)",
+            "container": "vLLM 0.6.2",
+            "status": "OK",
+            "tokensPerSecond": "18",
+            "notes": "--max-model-len 10000 --max-num-seqs 16 --enforce-eager",
+        },
         {
             "instanceType": "p4d.24xlarge",
             "quantization": "awq",