[CI/Build] Use uv in the Dockerfile (#13566)

Dockerfile

@@ -27,6 +27,9 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
     && ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \
     && curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION} \
     && python3 --version && python3 -m pip --version
+# Install uv for faster pip installs
+RUN --mount=type=cache,target=/root/.cache/pip \
+    python3 -m pip install uv
 
 # Upgrade to GCC 10 to avoid https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92519
 # as it was causing spam when compiling the CUTLASS kernels
@@ -52,13 +55,13 @@ WORKDIR /workspace
 # after this step
 RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
-        python3 -m pip install --index-url https://download.pytorch.org/whl/nightly/cu126 "torch==2.7.0.dev20250121+cu126" "torchvision==0.22.0.dev20250121";  \
+        uv pip install --system --index-url https://download.pytorch.org/whl/nightly/cu126 "torch==2.7.0.dev20250121+cu126" "torchvision==0.22.0.dev20250121";  \
     fi
 
 COPY requirements-common.txt requirements-common.txt
 COPY requirements-cuda.txt requirements-cuda.txt
 RUN --mount=type=cache,target=/root/.cache/pip \
-    python3 -m pip install -r requirements-cuda.txt
+    uv pip install --system -r requirements-cuda.txt
 
 # cuda arch list used by torch
 # can be useful for both `dev` and `test`
@@ -79,7 +82,7 @@ ARG TARGETPLATFORM
 COPY requirements-build.txt requirements-build.txt
 
 RUN --mount=type=cache,target=/root/.cache/pip \
-    python3 -m pip install -r requirements-build.txt
+    uv pip install --system -r requirements-build.txt
 
 COPY . .
 ARG GIT_REPO_CHECK=0
@@ -144,7 +147,7 @@ COPY requirements-lint.txt requirements-lint.txt
 COPY requirements-test.txt requirements-test.txt
 COPY requirements-dev.txt requirements-dev.txt
 RUN --mount=type=cache,target=/root/.cache/pip \
-    python3 -m pip install -r requirements-dev.txt
+    uv pip install --system -r requirements-dev.txt
 #################### DEV IMAGE ####################
 
 #################### vLLM installation IMAGE ####################
@@ -174,6 +177,9 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
     && ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \
     && curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION} \
     && python3 --version && python3 -m pip --version
+# Install uv for faster pip installs
+RUN --mount=type=cache,target=/root/.cache/pip \
+    python3 -m pip install uv
 
 # Workaround for https://github.com/openai/triton/issues/2507 and
 # https://github.com/pytorch/pytorch/issues/107960 -- hopefully
@@ -187,13 +193,13 @@ RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
 # after this step
 RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
-        python3 -m pip install --index-url https://download.pytorch.org/whl/nightly/cu124 "torch==2.6.0.dev20241210+cu124" "torchvision==0.22.0.dev20241215";  \
+        uv pip install --system --index-url https://download.pytorch.org/whl/nightly/cu124 "torch==2.6.0.dev20241210+cu124" "torchvision==0.22.0.dev20241215";  \
     fi
 
 # Install vllm wheel first, so that torch etc will be installed.
 RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \
     --mount=type=cache,target=/root/.cache/pip \
-    python3 -m pip install dist/*.whl --verbose
+    uv pip install --system dist/*.whl --verbose
 
 # If we need to build FlashInfer wheel before its release:
 # $ export FLASHINFER_ENABLE_AOT=1
@@ -210,7 +216,7 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
 RUN --mount=type=cache,target=/root/.cache/pip \
 . /etc/environment && \
 if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
-    python3 -m pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.1.post1/flashinfer_python-0.2.1.post1+cu124torch2.5-cp38-abi3-linux_x86_64.whl ; \
+    uv pip install --system https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.1.post1/flashinfer_python-0.2.1.post1+cu124torch2.5-cp38-abi3-linux_x86_64.whl ; \
 fi
 COPY examples examples
 
@@ -220,7 +226,7 @@ COPY examples examples
 # TODO: Remove this once FlashInfer AOT wheel is fixed
 COPY requirements-build.txt requirements-build.txt
 RUN --mount=type=cache,target=/root/.cache/pip \
-    python3 -m pip install -r requirements-build.txt
+    uv pip install --system -r requirements-build.txt
 
 #################### vLLM installation IMAGE ####################
 
@@ -233,15 +239,15 @@ ADD . /vllm-workspace/
 
 # install development dependencies (for testing)
 RUN --mount=type=cache,target=/root/.cache/pip \
-    python3 -m pip install -r requirements-dev.txt
+    uv pip install --system -r requirements-dev.txt
 
 # install development dependencies (for testing)
 RUN --mount=type=cache,target=/root/.cache/pip \
-    python3 -m pip install -e tests/vllm_test_utils
+    uv pip install --system -e tests/vllm_test_utils
 
 # enable fast downloads from hf (for testing)
 RUN --mount=type=cache,target=/root/.cache/pip \
-    python3 -m pip install hf_transfer
+    uv pip install --system hf_transfer
 ENV HF_HUB_ENABLE_HF_TRANSFER 1
 
 # Copy in the v1 package for testing (it isn't distributed yet)
@@ -262,9 +268,9 @@ FROM vllm-base AS vllm-openai-base
 # install additional dependencies for openai api server
 RUN --mount=type=cache,target=/root/.cache/pip \
     if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
-        pip install accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.42.0' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
+        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 \
-        pip install accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.45.0' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
+        uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.45.0' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
     fi
 
 ENV VLLM_USAGE_SOURCE production-docker-image