minor

Signed-off-by: Kinjal Patel <kinjalpravin@nvidia.com>

Author: kinjalpatel27

.github/workflows/gpu_tests.yml

@@ -40,20 +40,17 @@ jobs:
         include:
           - example: gpu
             timeout: 75
-            container_image: nvcr.io/nvidia/pytorch:26.04-py3
+            container_image: pytorch:26.04-py3
           - example: gpu_megatron
             timeout: 45
-            container_image: nvcr.io/nvidia/nemo:26.04
+            container_image: nemo:26.04
           - example: gpu_trtllm
             timeout: 30
-            container_image: nvcr.io/nvidia/tensorrt-llm/release:1.3.0rc16
-          - example: gpu_vllm
-            timeout: 30
-            container_image: docker.io/vllm/vllm-openai:v0.20.0
+            container_image: tensorrt-llm/release:1.3.0rc16
     runs-on: ${{ startsWith(github.ref, 'refs/heads/pull-request/') && 'linux-amd64-gpu-rtxpro6000-latest-1' || 'linux-amd64-gpu-rtxpro6000-latest-2' }}
     timeout-minutes: ${{ matrix.timeout }}
     container:
-      image: ${{ matrix.container_image }}
+      image: nvcr.io/nvidia/${{ matrix.container_image }}
       credentials:
         username: $oauthtoken
         password: ${{ secrets.NGC_API_KEY }}
@@ -75,7 +72,6 @@ jobs:
     runs-on: ${{ startsWith(github.ref, 'refs/heads/pull-request/') && 'linux-amd64-gpu-rtxpro6000-latest-1' || 'linux-amd64-gpu-rtxpro6000-latest-2' }}
     timeout-minutes: 30
     container:
-      # Keep in sync with examples/vllm_serve/Dockerfile.
       image: docker.io/vllm/vllm-openai:v0.20.0
       env:
         GIT_DEPTH: 1000 # For correct version