Revert precompile wheel changes (#22055)

docker/Dockerfile

@@ -206,7 +206,16 @@ ARG SCCACHE_REGION_NAME=us-west-2
 ARG SCCACHE_S3_NO_CREDENTIALS=0
 
 # Flag to control whether to use pre-built vLLM wheels
-ARG VLLM_USE_PRECOMPILED=""
+ARG VLLM_USE_PRECOMPILED
+# TODO: in setup.py VLLM_USE_PRECOMPILED is sensitive to truthiness, it will take =0 as "true", this should be fixed
+ENV VLLM_USE_PRECOMPILED=""
+RUN if [ "${VLLM_USE_PRECOMPILED}" = "1" ]; then \
+        export VLLM_USE_PRECOMPILED=1 && \
+        echo "Using precompiled wheels"; \
+    else \
+        unset VLLM_USE_PRECOMPILED && \
+        echo "Leaving VLLM_USE_PRECOMPILED unset to build wheels from source"; \
+    fi
 
 # if USE_SCCACHE is set, use sccache to speed up compilation
 RUN --mount=type=cache,target=/root/.cache/uv \
@@ -223,8 +232,6 @@ RUN --mount=type=cache,target=/root/.cache/uv \
         && export SCCACHE_S3_NO_CREDENTIALS=${SCCACHE_S3_NO_CREDENTIALS} \
         && export SCCACHE_IDLE_TIMEOUT=0 \
         && export CMAKE_BUILD_TYPE=Release \
-        && export VLLM_USE_PRECOMPILED="${VLLM_USE_PRECOMPILED}" \
-        && export VLLM_DOCKER_BUILD_CONTEXT=1 \
         && sccache --show-stats \
         && python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38 \
         && sccache --show-stats; \
@@ -238,22 +245,9 @@ RUN --mount=type=cache,target=/root/.cache/ccache \
         # Clean any existing CMake artifacts
         rm -rf .deps && \
         mkdir -p .deps && \
-        export VLLM_USE_PRECOMPILED="${VLLM_USE_PRECOMPILED}" && \
-        export VLLM_DOCKER_BUILD_CONTEXT=1 && \
         python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38; \
     fi
 
-# When using precompiled wheels, keep only the newest manylinux1 wheel and delete others
-RUN if [ "$VLLM_USE_PRECOMPILED" = "1" ]; then \
-        echo "Cleaning up extra wheels in dist/..." && \
-        # Identify the most recent manylinux1_x86_64 wheel
-        KEEP_WHEEL=$(ls -t dist/*manylinux1_x86_64.whl 2>/dev/null | head -n1) && \
-        if [ -n "$KEEP_WHEEL" ]; then \
-            echo "Keeping wheel: $KEEP_WHEEL"; \
-            find dist/ -type f -name "*.whl" ! -path "${KEEP_WHEEL}" -delete; \
-        fi; \
-    fi
-
 # Check the size of the wheel if RUN_WHEEL_CHECK is true
 COPY .buildkite/check-wheel-size.py check-wheel-size.py
 # sync the default value with .buildkite/check-wheel-size.py
@@ -369,7 +363,6 @@ RUN --mount=type=cache,target=/root/.cache/uv \
     fi
 
 # Install vllm wheel first, so that torch etc will be installed.
-# !bang
 RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \
     --mount=type=cache,target=/root/.cache/uv \
     uv pip install --system dist/*.whl --verbose \