fix: update inference processor from 'inf2' to 'neuronx' (#5488)

* fix: update inference processor from 'inf2' to 'neuronx'

The current version generates the following image tag for 0.4.1:
0.10.2-inf2-py310-sdk2.26.0-ubuntu22.04

But it should be:
0.10.2-neuronx-py310-sdk2.26.0-ubuntu22.04

* chore: add HF vllm neuron 0.4.2 image

* chore: add HF vllm neuron 0.4.4 image

Note that the actual SDK version is 2.26.1, but the images were published with a 2.26.0 tag.

* fix: 0.4.4 SDK version is actually 2.26.1

---------

Co-authored-by: Molly He <mollyhe@amazon.com>

Author: dacorvo

sagemaker-core/src/sagemaker/core/image_uri_config/huggingface-vllm-neuronx.json

@@ -1,10 +1,10 @@
 {
     "inference": {
         "processors": [
-            "inf2"
+            "neuronx"
         ],
         "version_aliases": {
-            "0.4": "0.4.1"
+            "0.4": "0.4.4"
         },
         "versions": {
             "0.4.1": {
@@ -27,12 +27,64 @@
                 "tag_prefix": "0.10.2",
                 "repository": "huggingface-vllm-inference-neuronx",
                 "container_version": {
-                    "inf2": "ubuntu22.04"
+                    "neuronx": "ubuntu22.04"
                 },
                 "sdk_versions": [
                     "sdk2.26.0"
                 ]
+            },
+            "0.4.2": {
+                "py_versions": [
+                    "py310"
+                ],
+                "registries": {
+                    "ap-northeast-1": "763104351884",
+                    "ap-south-1": "763104351884",
+                    "ap-southeast-1": "763104351884",
+                    "ap-southeast-2": "763104351884",
+                    "eu-central-1": "763104351884",
+                    "eu-west-1": "763104351884",
+                    "eu-west-3": "763104351884",
+                    "sa-east-1": "763104351884",
+                    "us-east-1": "763104351884",
+                    "us-east-2": "763104351884",
+                    "us-west-2": "763104351884"
+                },
+                "tag_prefix": "0.11.0-optimum0.4.2",
+                "repository": "huggingface-vllm-inference-neuronx",
+                "container_version": {
+                    "neuronx": "ubuntu22.04"
+                },
+                "sdk_versions": [
+                    "sdk2.26.0"
+                ]
+            },
+            "0.4.4": {
+                "py_versions": [
+                    "py310"
+                ],
+                "registries": {
+                    "ap-northeast-1": "763104351884",
+                    "ap-south-1": "763104351884",
+                    "ap-southeast-1": "763104351884",
+                    "ap-southeast-2": "763104351884",
+                    "eu-central-1": "763104351884",
+                    "eu-west-1": "763104351884",
+                    "eu-west-3": "763104351884",
+                    "sa-east-1": "763104351884",
+                    "us-east-1": "763104351884",
+                    "us-east-2": "763104351884",
+                    "us-west-2": "763104351884"
+                },
+                "tag_prefix": "0.11.0-optimum0.4.4",
+                "repository": "huggingface-vllm-inference-neuronx",
+                "container_version": {
+                    "neuronx": "ubuntu22.04"
+                },
+                "sdk_versions": [
+                    "sdk2.26.1"
+                ]
             }
         }
     }
-}
+}