Use pull through cache image for H100 pool (vllm-project#1518)

Signed-off-by: Kevin H. Luu <khluu000@gmail.com>

Author: khluu

.buildkite/test-merge.yml

@@ -24,7 +24,7 @@ steps:
       queue: "gpu_1_queue" # g6.4xlarge instance on AWS, has 1 L4 GPU
     plugins:
       - docker#v5.2.0:
-          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+          image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
           always-pull: true
           propagate-environment: true
           environment:
@@ -168,7 +168,7 @@ steps:
       - kubernetes:
           podSpec:
             containers:
-              - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
                 resources:
                   limits:
                     nvidia.com/gpu: 2
@@ -224,7 +224,7 @@ steps:
       - kubernetes:
           podSpec:
             containers:
-              - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
                 resources:
                   limits:
                     nvidia.com/gpu: 2
@@ -259,7 +259,7 @@ steps:
       - kubernetes:
           podSpec:
             containers:
-              - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+              - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
                 resources:
                   limits:
                     nvidia.com/gpu: 1
@@ -294,7 +294,7 @@ steps:
   #     - kubernetes:
   #         podSpec:
   #           containers:
-  #             - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+  #             - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
   #               resources:
   #                 limits:
   #                   nvidia.com/gpu: 1