Dockerfile: use uv pip everywhere (it's faster)

Dockerfile.ubi

@@ -32,7 +32,7 @@ ENV VIRTUAL_ENV=/opt/vllm
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 RUN microdnf install -y \
     python${PYTHON_VERSION}-devel python${PYTHON_VERSION}-pip python${PYTHON_VERSION}-wheel && \
-    python${PYTHON_VERSION} -m venv $VIRTUAL_ENV && pip install --no-cache -U pip wheel && microdnf clean all
+    python${PYTHON_VERSION} -m venv $VIRTUAL_ENV && pip install --no-cache -U pip wheel uv && microdnf clean all
 
 
 ## CUDA Base ###################################################################
@@ -57,9 +57,10 @@ ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 
 # install cuda and common dependencies
 RUN --mount=type=cache,target=/root/.cache/pip \
+    --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,source=requirements-common.txt,target=requirements-common.txt \
     --mount=type=bind,source=requirements-cuda.txt,target=requirements-cuda.txt \
-    pip install \
+    uv pip install \
         -r requirements-cuda.txt
 
 
@@ -68,13 +69,14 @@ FROM python-cuda-base AS dev
 
 # install build and runtime dependencies
 RUN --mount=type=cache,target=/root/.cache/pip \
+    --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,source=requirements-common.txt,target=requirements-common.txt \
     --mount=type=bind,source=requirements-cuda.txt,target=requirements-cuda.txt \
     --mount=type=bind,source=requirements-dev.txt,target=requirements-dev.txt \
     --mount=type=bind,source=requirements-lint.txt,target=requirements-lint.txt \
     --mount=type=bind,source=requirements-adag.txt,target=requirements-adag.txt \
     --mount=type=bind,source=requirements-test.txt,target=requirements-test.txt \
-    pip3 install \
+    uv pip install \
         -r requirements-cuda.txt \
         -r requirements-dev.txt
 
@@ -83,8 +85,9 @@ FROM dev AS build
 
 # install build dependencies
 RUN --mount=type=cache,target=/root/.cache/pip \
+    --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,source=requirements-build.txt,target=requirements-build.txt \
-    pip install -r requirements-build.txt
+    uv pip install -r requirements-build.txt
 
 # install compiler cache to speed up compilation leveraging local or remote caching
 # git is required for the cutlass kernels
@@ -121,6 +124,7 @@ COPY vllm vllm
 ENV CCACHE_DIR=/root/.cache/ccache
 RUN --mount=type=cache,target=/root/.cache/ccache \
     --mount=type=cache,target=/root/.cache/pip \
+    --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,src=.git,target=/workspace/.git \
     env CFLAGS="-march=haswell" \
         CXXFLAGS="$CFLAGS $CXXFLAGS" \
@@ -163,15 +167,17 @@ RUN microdnf install -y gcc \
 # install vllm wheel first, so that torch etc will be installed
 RUN --mount=type=bind,from=build,src=/workspace/dist,target=/workspace/dist \
     --mount=type=cache,target=/root/.cache/pip \
-    pip install $(echo dist/*.whl)'[tensorizer]' --verbose
+    --mount=type=cache,target=/root/.cache/uv \
+    uv pip install $(echo dist/*.whl)'[tensorizer]' --verbose
 
 # Install libsodium for Tensorizer encryption
 RUN --mount=type=bind,from=libsodium-builder,src=/usr/src/libsodium,target=/usr/src/libsodium \
     cd /usr/src/libsodium \
     && make install
 
 RUN --mount=type=cache,target=/root/.cache/pip \
-    pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.0.9/flashinfer-0.0.9+cu121torch2.3-cp311-cp311-linux_x86_64.whl
+    --mount=type=cache,target=/root/.cache/uv \
+    uv pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.0.9/flashinfer-0.0.9+cu121torch2.3-cp311-cp311-linux_x86_64.whl
 
 ENV HF_HUB_OFFLINE=1 \
     PORT=8000 \