change: Added ml.p4d and ml.p4de as supported instances for DeepSpeed (#3749)

Co-authored-by: EC2 Default User <[email protected]>

Author: andjsmi

src/sagemaker/djl_inference/defaults.py

@@ -47,6 +47,9 @@
     "ml.g4dn",
     "ml.g5",
     "ml.p3",
+    "ml.p3dn",
     "ml.p4",
+    "ml.p4d",
+    "ml.p4de",
     "local_gpu",
 }