[CI][torch nightlies] Use main Dockerfile with flags for nightly torch tests (#30443)

Signed-off-by: Orion Reblitz-Richardson <orionr@meta.com>
Signed-off-by: Orion Reblitz-Richardson <orionr@gmail.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>

docker/Dockerfile

@@ -148,12 +148,36 @@ ARG PYTORCH_CUDA_INDEX_BASE_URL
 
 WORKDIR /workspace
 
-# install build and runtime dependencies
+# We can specify the standard or nightly build of PyTorch
+ARG PYTORCH_NIGHTLY
+
+# Install build and runtime dependencies, including PyTorch
+# Check whether to install torch nightly instead of release for this build
 COPY requirements/common.txt requirements/common.txt
 COPY requirements/cuda.txt requirements/cuda.txt
+COPY use_existing_torch.py use_existing_torch.py
+COPY pyproject.toml pyproject.toml
 RUN --mount=type=cache,target=/root/.cache/uv \
+    if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
+        echo "Installing torch nightly..." \
+        && uv pip install --python /opt/venv/bin/python3 torch torchaudio torchvision --pre \
+        --index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
+        && echo "Installing other requirements..." \
+        && /opt/venv/bin/python3 use_existing_torch.py --prefix \
+        && uv pip install --python /opt/venv/bin/python3 -r requirements/cuda.txt \
+        --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+    else \
         uv pip install --python /opt/venv/bin/python3 -r requirements/cuda.txt \
-    --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
+        --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+    fi
+
+# Track PyTorch lib versions used during build and match in downstream instances.
+# We do this for both nightly and release so we can strip dependencies/*.txt as needed.
+# Otherwise library dependencies can upgrade/downgrade torch incorrectly.
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv pip freeze | grep -i "^torch=\|^torchvision=\|^torchaudio=" > torch_lib_versions.txt \
+    && TORCH_LIB_VERSIONS=$(cat torch_lib_versions.txt | xargs) \
+    && echo "Installed torch libs: ${TORCH_LIB_VERSIONS}"
 
 # CUDA arch list used by torch
 # Explicitly set the list to avoid issues with torch 2.2
@@ -171,8 +195,13 @@ ARG PIP_INDEX_URL UV_INDEX_URL
 ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
 ARG PYTORCH_CUDA_INDEX_BASE_URL
 
-# install build dependencies
+# We can specify the standard or nightly build of PyTorch
+ARG PYTORCH_NIGHTLY
+
+# Install build dependencies
 COPY requirements/build.txt requirements/build.txt
+COPY use_existing_torch.py use_existing_torch.py
+COPY --from=base /workspace/torch_lib_versions.txt torch_lib_versions.txt
 
 # This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
 # Reference: https://github.com/astral-sh/uv/pull/1694
@@ -182,8 +211,18 @@ ENV UV_INDEX_STRATEGY="unsafe-best-match"
 ENV UV_LINK_MODE=copy
 
 RUN --mount=type=cache,target=/root/.cache/uv \
-    uv pip install --python /opt/venv/bin/python3 -r requirements/build.txt \
-    --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
+    if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
+        echo "Installing build requirements without torch..." \
+        && python3 use_existing_torch.py --prefix \
+        && uv pip install --python /opt/venv/bin/python3 -r requirements/build.txt \
+        && echo "Installing torch nightly..." \
+        && uv pip install --python /opt/venv/bin/python3 $(cat torch_lib_versions.txt | grep -i "^torch=" | xargs) --pre \
+        --index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+    else \
+        echo "Installing build requirements..." \
+        && uv pip install --python /opt/venv/bin/python3 -r requirements/build.txt \
+        --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+    fi
 
 WORKDIR /workspace
 
@@ -215,6 +254,13 @@ ARG VLLM_MAIN_CUDA_VERSION=""
 # Use dummy version for csrc-build wheel (only .so files are extracted, version doesn't matter)
 ENV SETUPTOOLS_SCM_PRETEND_VERSION="0.0.0+csrc.build"
 
+# Use existing torch for nightly builds
+RUN --mount=type=cache,target=/root/.cache/uv \
+    if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
+        python3 use_existing_torch.py --prefix; \
+    fi
+
+# Build the vLLM wheel
 # if USE_SCCACHE is set, use sccache to speed up compilation
 RUN --mount=type=cache,target=/root/.cache/uv \
     if [ "$USE_SCCACHE" = "1" ]; then \
@@ -258,6 +304,7 @@ RUN --mount=type=cache,target=/root/.cache/ccache \
         export VLLM_DOCKER_BUILD_CONTEXT=1 && \
         python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38; \
     fi
+
 #################### CSRC BUILD IMAGE ####################
 
 #################### EXTENSIONS BUILD IMAGE ####################
@@ -314,8 +361,13 @@ ARG PIP_INDEX_URL UV_INDEX_URL
 ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
 ARG PYTORCH_CUDA_INDEX_BASE_URL
 
-# install build dependencies
+# We can specify the standard or nightly build of PyTorch
+ARG PYTORCH_NIGHTLY
+
+# Install build dependencies
 COPY requirements/build.txt requirements/build.txt
+COPY use_existing_torch.py use_existing_torch.py
+COPY --from=base /workspace/torch_lib_versions.txt torch_lib_versions.txt
 
 # This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
 # Reference: https://github.com/astral-sh/uv/pull/1694
@@ -325,14 +377,23 @@ ENV UV_INDEX_STRATEGY="unsafe-best-match"
 ENV UV_LINK_MODE=copy
 
 RUN --mount=type=cache,target=/root/.cache/uv \
-    uv pip install --python /opt/venv/bin/python3 -r requirements/build.txt \
-    --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
+    if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
+        echo "Installing build requirements without torch..." \
+        && python3 use_existing_torch.py --prefix \
+        && uv pip install --python /opt/venv/bin/python3 -r requirements/build.txt \
+        && echo "Installing torch nightly..." \
+        && uv pip install --python /opt/venv/bin/python3 $(cat torch_lib_versions.txt | grep -i "^torch=" | xargs) --pre \
+        --index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+    else \
+        echo "Installing build requirements..." \
+        && uv pip install --python /opt/venv/bin/python3 -r requirements/build.txt \
+        --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+    fi
 
 WORKDIR /workspace
 
 # Copy pre-built csrc wheel directly
 COPY --from=csrc-build /workspace/dist /precompiled-wheels
-
 COPY . .
 
 ARG GIT_REPO_CHECK=0
@@ -345,6 +406,13 @@ ENV VLLM_TARGET_DEVICE=${vllm_target_device}
 # Skip adding +precompiled suffix to version (preserves git-derived version)
 ENV VLLM_SKIP_PRECOMPILED_VERSION_SUFFIX=1
 
+# Use existing torch for nightly builds
+RUN --mount=type=cache,target=/root/.cache/uv \
+    if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
+        python3 use_existing_torch.py --prefix; \
+    fi
+
+# Build the vLLM wheel
 RUN --mount=type=cache,target=/root/.cache/uv \
     --mount=type=bind,source=.git,target=.git \
     if [ "${vllm_target_device}" = "cuda" ]; then \
@@ -367,7 +435,8 @@ RUN if [ "$RUN_WHEEL_CHECK" = "true" ]; then \
     else \
         echo "Skipping wheel size check."; \
     fi
-#################### EXTENSION Build IMAGE ####################
+
+#################### WHEEL BUILD IMAGE ####################
 
 #################### DEV IMAGE ####################
 FROM base AS dev
@@ -385,12 +454,34 @@ ENV UV_LINK_MODE=copy
 
 # Install libnuma-dev, required by fastsafetensors (fixes #20384)
 RUN apt-get update && apt-get install -y --no-install-recommends libnuma-dev && rm -rf /var/lib/apt/lists/*
+
+
+# We can specify the standard or nightly build of PyTorch
+ARG PYTORCH_NIGHTLY
+
+# Install development dependencies
 COPY requirements/lint.txt requirements/lint.txt
+COPY requirements/test.in requirements/test.in
 COPY requirements/test.txt requirements/test.txt
 COPY requirements/dev.txt requirements/dev.txt
+COPY use_existing_torch.py use_existing_torch.py
+COPY --from=base /workspace/torch_lib_versions.txt torch_lib_versions.txt
 RUN --mount=type=cache,target=/root/.cache/uv \
-    uv pip install --python /opt/venv/bin/python3 -r requirements/dev.txt \
-    --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
+    if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
+        echo "Installing dev requirements plus torch nightly..." \
+        && python3 use_existing_torch.py --prefix \
+        && cat torch_lib_versions.txt >> requirements/test.in \
+        && uv pip compile requirements/test.in -o requirements/test.txt --index-strategy unsafe-best-match \
+        --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
+        && uv pip install --python /opt/venv/bin/python3 $(cat torch_lib_versions.txt | xargs) --pre \
+        -r requirements/dev.txt \
+        --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+    else \
+        echo "Installing dev requirements..." \
+        && uv pip install --python /opt/venv/bin/python3 -r requirements/dev.txt \
+        --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+    fi
+
 #################### DEV IMAGE ####################
 #################### vLLM installation IMAGE ####################
 # image with vLLM installed
@@ -548,11 +639,26 @@ ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
 ARG PYTORCH_CUDA_INDEX_BASE_URL
 ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
 
-# Install vllm wheel first, so that torch etc will be installed.
+# We can specify the standard or nightly build of PyTorch
+ARG PYTORCH_NIGHTLY
+
+# Install vLLM wheel first, so that torch etc will be installed.
+# Check whether to install torch nightly instead of release for this build.
+COPY --from=base /workspace/torch_lib_versions.txt torch_lib_versions.txt
 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 \
-        --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
+    if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
+        echo "Installing torch nightly..." \
+        && uv pip install --system $(cat torch_lib_versions.txt | xargs) --pre \
+        --index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
+        && echo "Installing vLLM..." \
+        && uv pip install --system dist/*.whl --verbose \
+        --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+    else \
+        echo "Installing vLLM..." \
+        && uv pip install --system dist/*.whl --verbose \
+        --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+    fi
 
 RUN --mount=type=cache,target=/root/.cache/uv \
 . /etc/environment && \
@@ -612,12 +718,33 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
     && apt-get update -y \
     && apt-get install -y git
 
-# install development dependencies (for testing)
+# We can specify the standard or nightly build of PyTorch
+ARG PYTORCH_NIGHTLY
+
+# Install development dependencies (for testing)
+COPY requirements/lint.txt requirements/lint.txt
+COPY requirements/test.in requirements/test.in
+COPY requirements/test.txt requirements/test.txt
+COPY requirements/dev.txt requirements/dev.txt
+COPY use_existing_torch.py use_existing_torch.py
+COPY --from=base /workspace/torch_lib_versions.txt torch_lib_versions.txt
 RUN --mount=type=cache,target=/root/.cache/uv \
     CUDA_MAJOR="${CUDA_VERSION%%.*}"; \
     if [ "$CUDA_MAJOR" -ge 12 ]; then \
-        uv pip install --system -r requirements/dev.txt \
+        if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
+            echo "Installing dev requirements plus torch nightly..." \
+            && python3 use_existing_torch.py --prefix \
+            && cat torch_lib_versions.txt >> requirements/test.in \
+            && uv pip compile requirements/test.in -o requirements/test.txt --index-strategy unsafe-best-match \
+            --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
+            && uv pip install --system $(cat torch_lib_versions.txt | xargs) --pre \
+            -r requirements/dev.txt \
+            --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+        else \
+            echo "Installing dev requirements..." \
+            && uv pip install --system -r requirements/dev.txt \
             --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
+        fi \
     fi
 
 # install development dependencies (for testing)

docker/Dockerfile.nightly_torch

+#######
+#
+# THIS FILE IS DEPRECATED AND WILL BE REMOVED SHORTLY
+#
+# Please use the standard Dockerfile with PYTORCH_NIGHTLY=1 instead
+#
+#######
+
 # The vLLM Dockerfile is used to construct vLLM image against torch nightly that can be directly used for testing
 
 # for torch nightly, cuda >=12.6 is required,

use_existing_torch.py

 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
+import argparse
 import glob
+import sys
 
-for file in (*glob.glob("requirements/*.txt"), "pyproject.toml"):
-    print(f">>> cleaning {file}")
+# Only strip targeted libraries when checking prefix
+TORCH_LIB_PREFIXES = (
+    # requirements/*.txt/in
+    "torch=",
+    "torchvision=",
+    "torchaudio=",
+    # pyproject.toml
+    '"torch =',
+    '"torchvision =',
+    '"torchaudio =',
+)
+
+
+def main(argv):
+    parser = argparse.ArgumentParser(
+        description="Strip torch lib requirements to use installed version."
+    )
+    parser.add_argument(
+        "--prefix",
+        action="store_true",
+        help="Strip prefix matches only (default: False)",
+    )
+    args = parser.parse_args(argv)
+
+    for file in (
+        *glob.glob("requirements/*.txt"),
+        *glob.glob("requirements/*.in"),
+        "pyproject.toml",
+    ):
         with open(file) as f:
             lines = f.readlines()
         if "torch" in "".join(lines).lower():
-        print("removed:")
             with open(file, "w") as f:
                 for line in lines:
-                if "torch" not in line.lower():
+                    if (
+                        args.prefix
+                        and not line.lower().strip().startswith(TORCH_LIB_PREFIXES)
+                        or not args.prefix
+                        and "torch" not in line.lower()
+                    ):
                         f.write(line)
                     else:
-                    print(line.strip())
-    print(f"<<< done cleaning {file}\n")
+                        print(f">>> removed from {file}:", line.strip())
+
+
+if __name__ == "__main__":
+    main(sys.argv[1:])