Create llama3-70b.json

inference-cache-config/llama3-70b.json

@@ -0,0 +1,16 @@
+{
+  "meta-llama/Meta-Llama-3-70B": [
+    {
+      "batch_size": 1,
+      "sequence_length": 4096,
+      "num_cores": 24,
+      "auto_cast_type": "fp16"
+    },
+    {
+      "batch_size": 4,
+      "sequence_length": 4096,
+      "num_cores": 24,
+      "auto_cast_type": "fp16"
+    }
+  ]
+}