latest tgi (#5255)

* latest tgi

* add optimum-neuron tgi

---------

Co-authored-by: sage-maker <[email protected]>

Author: pagezyhf

src/sagemaker/image_uri_config/huggingface-llm-neuronx.json

@@ -4,7 +4,8 @@
             "inf2"
         ],
         "version_aliases": {
-            "0.0": "0.0.28"
+            "0.0": "0.0.28",
+            "0.2": "0.2.0"
         },
         "versions": {
             "0.0.16": {
@@ -654,6 +655,60 @@
                 "container_version": {
                     "inf2": "ubuntu22.04"
                 }
+            },
+            "0.2.0": {
+                "py_versions": [
+                    "py310"
+                ],
+                "registries": {
+                    "af-south-1": "626614931356",
+                    "ap-east-1": "871362719292",
+                    "ap-east-2": "975050140332",
+                    "ap-northeast-1": "763104351884",
+                    "ap-northeast-2": "763104351884",
+                    "ap-northeast-3": "364406365360",
+                    "ap-south-1": "763104351884",
+                    "ap-south-2": "772153158452",
+                    "ap-southeast-1": "763104351884",
+                    "ap-southeast-2": "763104351884",
+                    "ap-southeast-3": "907027046896",
+                    "ap-southeast-4": "457447274322",
+                    "ap-southeast-5": "550225433462",
+                    "ap-southeast-6": "633930458069",
+                    "ap-southeast-7": "590183813437",
+                    "ca-central-1": "763104351884",
+                    "ca-west-1": "204538143572",
+                    "cn-north-1": "727897471807",
+                    "cn-northwest-1": "727897471807",
+                    "eu-central-1": "763104351884",
+                    "eu-central-2": "380420809688",
+                    "eu-north-1": "763104351884",
+                    "eu-south-1": "692866216735",
+                    "eu-south-2": "503227376785",
+                    "eu-west-1": "763104351884",
+                    "eu-west-2": "763104351884",
+                    "eu-west-3": "763104351884",
+                    "il-central-1": "780543022126",
+                    "me-central-1": "914824155844",
+                    "me-south-1": "217643126080",
+                    "mx-central-1": "637423239942",
+                    "sa-east-1": "763104351884",
+                    "us-east-1": "763104351884",
+                    "us-east-2": "763104351884",
+                    "us-gov-east-1": "446045086412",
+                    "us-gov-west-1": "442386744353",
+                    "us-iso-east-1": "886529160074",
+                    "us-isob-east-1": "094389454867",
+                    "us-isof-east-1": "303241398832",
+                    "us-isof-south-1": "454834333376",
+                    "us-west-1": "763104351884",
+                    "us-west-2": "763104351884"
+                },
+                "tag_prefix": "2.5.1-optimum3.3.4",
+                "repository": "huggingface-pytorch-tgi-inference",
+                "container_version": {
+                    "inf2": "ubuntu22.04"
+                }
             }
         }
     }

src/sagemaker/image_uri_config/huggingface-llm.json

@@ -16,7 +16,8 @@
             "2.3": "2.3.1",
             "3.0": "3.0.1",
             "3.2": "3.2.3",
-            "3.1": "3.1.1"
+            "3.1": "3.1.1",
+            "3.3": "3.3.4"
         },
         "versions": {
             "0.6.0": {
@@ -1152,6 +1153,59 @@
                 "container_version": {
                     "gpu": "cu124-ubuntu22.04"
                 }
+            },
+            "3.3.4": {
+                "py_versions": [
+                    "py311"
+                ],
+                "registries": {
+                    "af-south-1": "626614931356",
+                    "ap-east-1": "871362719292",
+                    "ap-east-2": "975050140332",
+                    "ap-northeast-1": "763104351884",
+                    "ap-northeast-2": "763104351884",
+                    "ap-northeast-3": "364406365360",
+                    "ap-south-1": "763104351884",
+                    "ap-south-2": "772153158452",
+                    "ap-southeast-1": "763104351884",
+                    "ap-southeast-2": "763104351884",
+                    "ap-southeast-3": "907027046896",
+                    "ap-southeast-4": "457447274322",
+                    "ap-southeast-5": "550225433462",
+                    "ap-southeast-7": "590183813437",
+                    "ca-central-1": "763104351884",
+                    "ca-west-1": "204538143572",
+                    "cn-north-1": "727897471807",
+                    "cn-northwest-1": "727897471807",
+                    "eu-central-1": "763104351884",
+                    "eu-central-2": "380420809688",
+                    "eu-north-1": "763104351884",
+                    "eu-south-1": "692866216735",
+                    "eu-south-2": "503227376785",
+                    "eu-west-1": "763104351884",
+                    "eu-west-2": "763104351884",
+                    "eu-west-3": "763104351884",
+                    "il-central-1": "780543022126",
+                    "me-central-1": "914824155844",
+                    "me-south-1": "217643126080",
+                    "mx-central-1": "637423239942",
+                    "sa-east-1": "763104351884",
+                    "us-east-1": "763104351884",
+                    "us-east-2": "763104351884",
+                    "us-gov-east-1": "446045086412",
+                    "us-gov-west-1": "442386744353",
+                    "us-iso-east-1": "886529160074",
+                    "us-isob-east-1": "094389454867",
+                    "us-isof-east-1": "303241398832",
+                    "us-isof-south-1": "454834333376",
+                    "us-west-1": "763104351884",
+                    "us-west-2": "763104351884"
+                },
+                "tag_prefix": "2.7.0-tgi3.3.4",
+                "repository": "huggingface-pytorch-tgi-inference",
+                "container_version": {
+                    "gpu": "cu124-ubuntu22.04"
+                }
             }
         }
     }