[CI] add kvcache-connector dependency definition and add into CI build (#18193)

Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>

.buildkite/release-pipeline.yaml

@@ -52,7 +52,7 @@ steps:
       queue: cpu_queue_postmerge
     commands:
       - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.8.1 --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT --target vllm-openai --progress plain -f docker/Dockerfile ."
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg USE_SCCACHE=1 --build-arg GIT_REPO_CHECK=1 --build-arg CUDA_VERSION=12.8.1 --build-arg INSTALL_KV_CONNECTORS=true --tag public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT --target vllm-openai --progress plain -f docker/Dockerfile ."
       - "docker push public.ecr.aws/q9t5s3a7/vllm-release-repo:$BUILDKITE_COMMIT"
 
   - label: "Annotate release workflow"

docker/Dockerfile

+
 # The vLLM Dockerfile is used to construct vLLM image that can be directly used
 # to run the OpenAI compatible server.
 
@@ -62,12 +63,16 @@ ARG PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly
 ARG PIP_KEYRING_PROVIDER=disabled
 ARG UV_KEYRING_PROVIDER=${PIP_KEYRING_PROVIDER}
 
+# Flag enables build-in KV-connector dependency libs into docker images
+ARG INSTALL_KV_CONNECTORS=false
+
 #################### BASE BUILD IMAGE ####################
 # prepare basic build environment
 FROM ${BUILD_BASE_IMAGE} AS base
 ARG CUDA_VERSION
 ARG PYTHON_VERSION
 ARG TARGETPLATFORM
+ARG INSTALL_KV_CONNECTORS=false
 ENV DEBIAN_FRONTEND=noninteractive
 
 ARG DEADSNAKES_MIRROR_URL
@@ -276,6 +281,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
 FROM ${FINAL_BASE_IMAGE} AS vllm-base
 ARG CUDA_VERSION
 ARG PYTHON_VERSION
+ARG INSTALL_KV_CONNECTORS=false
 WORKDIR /vllm-workspace
 ENV DEBIAN_FRONTEND=noninteractive
 ARG TARGETPLATFORM
@@ -485,6 +491,7 @@ RUN mv mkdocs.yaml test_docs/
 # base openai image with additional requirements, for any subsequent openai-style images
 FROM vllm-base AS vllm-openai-base
 ARG TARGETPLATFORM
+ARG INSTALL_KV_CONNECTORS=false
 
 ARG PIP_INDEX_URL UV_INDEX_URL
 ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
@@ -493,8 +500,13 @@ ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
 # Reference: https://github.com/astral-sh/uv/pull/1694
 ENV UV_HTTP_TIMEOUT=500
 
+COPY requirements/kv_connectors.txt requirements/kv_connectors.txt
+
 # install additional dependencies for openai api server
 RUN --mount=type=cache,target=/root/.cache/uv \
+    if [ "$INSTALL_KV_CONNECTORS" = "true" ]; then \
+        uv pip install --system -r requirements/kv_connectors.txt; \
+    fi; \
     if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
         uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.42.0' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
     else \

requirements/kv_connectors.txt

+lmcache
\ No newline at end of file