From 5b29c958c713d367c7caf9313529d4fb2dd6b762 Mon Sep 17 00:00:00 2001 From: Yan Ma Date: Wed, 29 Jul 2026 16:24:56 +0800 Subject: [PATCH] [XPU] upgrade to torch 2.13 (#48677) Signed-off-by: Yan Ma Signed-off-by: Kunshang Ji Co-authored-by: Kunshang Ji Co-authored-by: Cyrus Leung --- .../scripts/hardware_ci/run-intel-test.sh | 2 +- docker/Dockerfile.xpu | 37 +------------- .../installation/gpu.xpu.inc.md | 4 +- requirements/test/xpu.txt | 50 ++++++++++--------- requirements/xpu.txt | 6 +-- setup.py | 2 +- vllm/_custom_ops.py | 26 ---------- 7 files changed, 35 insertions(+), 92 deletions(-) diff --git a/.buildkite/scripts/hardware_ci/run-intel-test.sh b/.buildkite/scripts/hardware_ci/run-intel-test.sh index 83cde9ad16..edbb771623 100755 --- a/.buildkite/scripts/hardware_ci/run-intel-test.sh +++ b/.buildkite/scripts/hardware_ci/run-intel-test.sh @@ -369,7 +369,7 @@ export HF_TOKEN ZE_AFFINITY_MASK -e CMDS \ --name "${container_name}" \ "${IMAGE}" \ - bash -c 'set -e; source /opt/intel/oneapi/setvars.sh --force; source /opt/intel/oneapi/ccl/2021.15/env/vars.sh --force; echo "ZE_AFFINITY_MASK is ${ZE_AFFINITY_MASK:-}"; eval "$CMDS"' \ + bash -c 'set -e; echo "ZE_AFFINITY_MASK is ${ZE_AFFINITY_MASK:-}"; eval "$CMDS"' \ >/dev/null } 9>/tmp/docker-pull.lock diff --git a/docker/Dockerfile.xpu b/docker/Dockerfile.xpu index 3bd16e8629..c3b72d1af6 100644 --- a/docker/Dockerfile.xpu +++ b/docker/Dockerfile.xpu @@ -63,21 +63,6 @@ RUN apt-get update -y && \ python3-pip && \ rm -rf /var/lib/apt/lists/* -# Add oneAPI repo, pin oneAPI to 2025.3, then install pinned packages in one layer. -RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && \ - echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list && \ - printf '%s\n' \ - 'Package: intel-oneapi-* intel-deep-learning-essentials* intel-pti*' \ - 'Pin: version 2025.3*' \ - 'Pin-Priority: 1001' \ - > /etc/apt/preferences.d/oneapi-2025.3.pref && \ - apt-get update -y && \ - apt-get install -y --no-install-recommends \ - intel-oneapi-compiler-dpcpp-cpp-2025.3 \ - intel-oneapi-mkl-devel-2025.3 \ - intel-oneapi-dnnl-devel-2025.3 && \ - rm -rf /var/lib/apt/lists/* - # Install UMD RUN mkdir neo && \ cd neo && \ @@ -100,22 +85,6 @@ RUN curl -LsSf https://astral.sh/uv/install.sh | sh \ && uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV} ENV PATH="$VIRTUAL_ENV/bin:$PATH" -# This oneccl contains the BMG support which is not the case for default version of oneapi 2025.3. -ARG ONECCL_INSTALLER="intel-oneccl-2021.15.9.14_offline.sh" -RUN wget "https://github.com/uxlfoundation/oneCCL/releases/download/2021.15.9/${ONECCL_INSTALLER}" && \ - bash "${ONECCL_INSTALLER}" -a --silent --eula accept && \ - rm "${ONECCL_INSTALLER}" && \ - echo "source /opt/intel/oneapi/setvars.sh --force" >> /root/.bashrc && \ - echo "source /opt/intel/oneapi/ccl/2021.15/env/vars.sh --force" >> /root/.bashrc && \ - rm -f /opt/intel/oneapi/ccl/latest && \ - ln -s /opt/intel/oneapi/ccl/2021.15 /opt/intel/oneapi/ccl/latest && \ - printf '%s\n' \ - '/opt/intel/oneapi/ccl/2021.15/lib' \ - '/opt/intel/oneapi/mpi/2021.15/lib' \ - '/opt/intel/oneapi/compiler/2025.3/lib' \ - > /etc/ld.so.conf.d/oneapi-ccl.conf && \ - ldconfig - SHELL ["bash", "-c"] CMD ["bash", "-c", "source /root/.bashrc && exec bash"] @@ -135,8 +104,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \ uv pip install --upgrade pip - -ENV LD_LIBRARY_PATH=/opt/intel/oneapi/ccl/2021.15/lib:/opt/intel/oneapi/mpi/2021.15/lib:/opt/intel/oneapi/compiler/2025.3/lib:/usr/local/lib +ENV LD_LIBRARY_PATH=/opt/venv/lib:/usr/local/lib CMD ["/bin/bash"] ######################### UCX + NIXL BUILD STAGE ######################### @@ -216,8 +184,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \ uv pip install -r /workspace/vllm/requirements/xpu.txt && \ uv pip install --no-build-isolation -r /workspace/vllm/requirements/test/xpu.txt && \ uv pip uninstall triton triton-xpu && \ - uv pip install triton-xpu==3.7.1 && \ - uv pip uninstall oneccl oneccl-devel + uv pip install triton-xpu==3.7.2 # Keep source-dependent layers near the end so frequent code-only changes # don't invalidate heavy dependency and UCX/NIXL layers. diff --git a/docs/getting_started/installation/gpu.xpu.inc.md b/docs/getting_started/installation/gpu.xpu.inc.md index e4c1aec71c..ef207c8d83 100644 --- a/docs/getting_started/installation/gpu.xpu.inc.md +++ b/docs/getting_started/installation/gpu.xpu.inc.md @@ -42,12 +42,12 @@ pip install -v -r requirements/xpu.txt ```bash pip uninstall -y triton triton-xpu - pip install triton-xpu==3.7.1 --extra-index-url https://download.pytorch.org/whl/xpu + pip install triton-xpu==3.7.2 --extra-index-url https://download.pytorch.org/whl/xpu ``` !!! note - `triton` (without suffix) is for NVIDIA GPUs only. On XPU, using it instead of `triton-xpu` can cause correctness or runtime issues. - - For torch 2.12 (the version used in `requirements/xpu.txt`), the matching package is `triton-xpu==3.7.1`. If you use a different version of torch, check the corresponding `triton-xpu` version in [docker/Dockerfile.xpu](https://github.com/vllm-project/vllm/blob/main/docker/Dockerfile.xpu). + - For torch 2.13 (the version used in `requirements/xpu.txt`), the matching package is `triton-xpu==3.7.2`. If you use a different version of torch, check the corresponding `triton-xpu` version in [docker/Dockerfile.xpu](https://github.com/vllm-project/vllm/blob/main/docker/Dockerfile.xpu). - Finally, build and install vLLM XPU backend: diff --git a/requirements/test/xpu.txt b/requirements/test/xpu.txt index 60ea4f5189..30fdee5025 100644 --- a/requirements/test/xpu.txt +++ b/requirements/test/xpu.txt @@ -140,7 +140,7 @@ docopt==0.6.2 # via num2words docstring-parser==0.18.0 # via anthropic -dpcpp-cpp-rt==2025.3.2 +dpcpp-cpp-rt==2026.0.0 # via # onemkl-sycl-blas # onemkl-sycl-dft @@ -253,27 +253,27 @@ ijson==3.5.0 # via -r requirements/test/../common.txt imageio==2.37.3 # via scikit-image -impi-rt==2021.17.2 +impi-rt==2021.18.0 # via # oneccl # torch iniconfig==2.3.0 # via pytest -intel-cmplr-lib-rt==2025.3.2 +intel-cmplr-lib-rt==2026.0.0 # via # intel-sycl-rt # torch -intel-cmplr-lib-ur==2025.3.2 +intel-cmplr-lib-ur==2026.0.0 # via # intel-openmp # intel-sycl-rt # torch -intel-cmplr-lic-rt==2025.3.2 +intel-cmplr-lic-rt==2026.0.0 # via # intel-opencl-rt # intel-sycl-rt # torch -intel-opencl-rt==2025.3.2 +intel-opencl-rt==2026.0.0 # via # dpcpp-cpp-rt # onemkl-sycl-blas @@ -282,14 +282,14 @@ intel-opencl-rt==2025.3.2 # onemkl-sycl-rng # onemkl-sycl-sparse # torch -intel-openmp==2025.3.2 +intel-openmp==2026.0.0 # via # dpcpp-cpp-rt # mkl # torch -intel-pti==0.16.0 +intel-pti==0.17.0 # via torch -intel-sycl-rt==2025.3.2 +intel-sycl-rt==2026.0.0 # via # dpcpp-cpp-rt # oneccl @@ -378,7 +378,7 @@ mistral-common==1.11.5 # -c requirements/common.txt # -r requirements/test/../common.txt # -r requirements/test/xpu.in -mkl==2025.3.1 +mkl==2026.0.0 # via # onemkl-sycl-blas # onemkl-sycl-dft @@ -453,28 +453,28 @@ numpy==2.2.6 # torchvision # transformers # xgrammar -oneccl==2021.17.2 +oneccl==2022.0.0 # via # oneccl-devel # torch -oneccl-devel==2021.17.2 +oneccl-devel==2022.0.0 # via torch -onemkl-license==2025.3.1 +onemkl-license==2026.0.0 # via # mkl # torch -onemkl-sycl-blas==2025.3.1 +onemkl-sycl-blas==2026.0.0 # via # onemkl-sycl-lapack # onemkl-sycl-sparse # torch -onemkl-sycl-dft==2025.3.1 +onemkl-sycl-dft==2026.0.0 # via torch -onemkl-sycl-lapack==2025.3.1 +onemkl-sycl-lapack==2026.0.0 # via torch -onemkl-sycl-rng==2025.3.1 +onemkl-sycl-rng==2026.0.0 # via torch -onemkl-sycl-sparse==2025.3.1 +onemkl-sycl-sparse==2026.0.0 # via torch openai==2.44.0 # via @@ -719,6 +719,8 @@ pyyaml==6.0.3 # timm # transformers # uvicorn +pyzes==0.1.1 + # via torch pyzmq==27.1.0 # via # -c requirements/common.txt @@ -871,14 +873,14 @@ tabledata==1.3.4 # via pytablewriter tabulate==0.10.0 # via sacrebleu -tbb==2022.3.1 +tbb==2023.0.0 # via # intel-opencl-rt # mkl # torch tblib==3.1.0 # via -r requirements/test/xpu.in -tcmlib==1.4.1 +tcmlib==1.5.0 # via # tbb # torch @@ -910,7 +912,7 @@ tokenizers==0.22.2 # -c requirements/common.txt # -r requirements/test/../common.txt # transformers -torch==2.12.0+xpu +torch==2.13.0+xpu # via # -c requirements/xpu.txt # accelerate @@ -920,7 +922,7 @@ torch==2.12.0+xpu # timm # torchvision # xgrammar -torchvision==0.27.0+xpu +torchvision==0.28.0+xpu # via timm tqdm==4.67.3 # via @@ -946,7 +948,7 @@ transformers==5.14.1 # xgrammar triton==3.7.1 # via xgrammar -triton-xpu==3.7.1 +triton-xpu==3.7.2 # via torch typepy==1.3.4 # via @@ -1001,7 +1003,7 @@ typing-inspection==0.4.2 # mcp # pydantic # pydantic-settings -umf==1.0.3 +umf==1.1.0 # via # intel-cmplr-lib-ur # torch diff --git a/requirements/xpu.txt b/requirements/xpu.txt index 8ae5649b20..dc81cce64f 100644 --- a/requirements/xpu.txt +++ b/requirements/xpu.txt @@ -12,10 +12,10 @@ jinja2>=3.1.6 datasets # for benchmark scripts numba == 0.65.0 # Required for N-gram speculative decoding --extra-index-url=https://download.pytorch.org/whl/xpu -torch==2.12.0 +torch==2.13.0 torchaudio torchvision torchcodec >= 0.14 # Required for the torchcodec video decoding backend -auto_round_lib==0.14.1 -vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.11.1/vllm_xpu_kernels-0.1.11.1-cp38-abi3-manylinux_2_28_x86_64.whl +auto_round_lib==0.14.2 +vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.12/vllm_xpu_kernels-0.1.12-cp38-abi3-manylinux_2_28_x86_64.whl diff --git a/setup.py b/setup.py index baa359d0b9..a874b37278 100644 --- a/setup.py +++ b/setup.py @@ -1122,7 +1122,7 @@ if _is_cuda() or _is_hip(): # copying the relevant .py files from the source repository. ext_modules.append(CMakeExtension(name="vllm.triton_kernels", optional=True)) -if sys.version_info >= (3, 11): +if not _is_xpu() and sys.version_info >= (3, 11): ext_modules.append(CMakeExtension(name="vllm.spinloop")) ext_modules.append(CMakeExtension(name="vllm.fs_io_C")) diff --git a/vllm/_custom_ops.py b/vllm/_custom_ops.py index 1e1e689083..93910c544c 100644 --- a/vllm/_custom_ops.py +++ b/vllm/_custom_ops.py @@ -2391,17 +2391,6 @@ def topk_softmax( e_score_correction_bias: torch.Tensor | None = None, is_padding: torch.Tensor | None = None, ) -> None: - if current_platform.is_xpu(): - # TODO: Remove after vllm-xpu-kernels supports is_padding. - torch.ops._moe_C.topk_softmax( - topk_weights, - topk_ids, - token_expert_indices, - gating_output, - renormalize, - e_score_correction_bias, - ) - return torch.ops._moe_C.topk_softmax( topk_weights, topk_ids, @@ -2447,21 +2436,6 @@ def topk_hash_softplus_sqrt( hash_indices_table: torch.Tensor | None = None, is_padding: torch.Tensor | None = None, ) -> None: - if current_platform.is_xpu(): - # TODO: Remove after vllm-xpu-kernels supports is_padding. - torch.ops._moe_C.topk_softplus_sqrt( - topk_weights, - topk_indices, - token_expert_indices, - gating_output, - renormalize, - routed_scaling_factor, - e_score_correction_bias, - input_tokens, - hash_indices_table, - ) - return - torch.ops._moe_C.topk_softplus_sqrt( topk_weights, topk_indices,