Merge branch 'master' into patch

Author: sirutBuasai

huggingface/vllm/buildspec.yml

@@ -42,9 +42,7 @@ images:
     tag_python_version: &TAG_PYTHON_VERSION py312
     os_version: &OS_VERSION ubuntu22.04
     transformers_version: &TRANSFORMERS_VERSION 4.57.3
-    vllm_version: &VLLM_VERSION 0.14.0
-    tag: !join [ "vllm", "-", *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
-    latest_release_tag: !join [ "vllm", "-", *VERSION, "-", *DEVICE_TYPE, "-", *TAG_PYTHON_VERSION, "-", *CUDA_VERSION, "-", *OS_VERSION, "-sagemaker" ]
+    tag: !join [ *VERSION, '-', 'transformers', *TRANSFORMERS_VERSION, '-', *DEVICE_TYPE, '-', *TAG_PYTHON_VERSION, '-', *CUDA_VERSION, '-', *OS_VERSION ]
     docker_file: !join [ docker/, *SHORT_VERSION, /, *CUDA_VERSION, /Dockerfile ]
     target: sagemaker
     build: true
@@ -53,4 +51,4 @@ images:
       test_platforms:
         - sanity
         - security
-        - sagemaker
+        - sagemaker

release_images_general.yml

@@ -176,3 +176,17 @@ release_images:
       force_release: False
       public_registry: True
       enable_soci: True
+  13:
+    framework: "huggingface_vllm"
+    version: "0.14.0"
+    arch_type: "x86"
+    hf_transformers: "4.57.3"
+    vllm_version: "0.14.0"
+    general:  # vLLM is categorized as general type
+      device_types: [ "gpu" ]
+      python_versions: [ "py312" ]
+      os_version: "ubuntu22.04"
+      cuda_version: "cu129"
+      example: False
+      disable_sm_tag: True
+      force_release: False