From ec67d7ae619435f5f27279081f40e3a733ca9ab7 Mon Sep 17 00:00:00 2001 From: Kunshang Ji Date: Fri, 19 Jun 2026 15:37:20 +0800 Subject: [PATCH] [xpu] bump up vllm-xpu-kernels v0.1.10 and upgrade 2618 umd (#40367) Signed-off-by: Kunshang Ji Signed-off-by: Kunshang Ji --- .buildkite/intel_jobs/test-intel.yaml | 2 +- docker/Dockerfile.xpu | 14 +++++++------- docs/getting_started/installation/gpu.xpu.inc.md | 1 + requirements/xpu.txt | 2 +- 4 files changed, 10 insertions(+), 9 deletions(-) diff --git a/.buildkite/intel_jobs/test-intel.yaml b/.buildkite/intel_jobs/test-intel.yaml index 7ca48e6841..f365bf7651 100644 --- a/.buildkite/intel_jobs/test-intel.yaml +++ b/.buildkite/intel_jobs/test-intel.yaml @@ -67,7 +67,7 @@ steps: pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py --ignore=v1/worker/test_worker_memory_snapshot.py && pytest -v -s v1/structured_output && pytest -v -s v1/test_serial_utils.py && - pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py && + pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py --ignore=v1/spec_decode/test_speculators_correctness.py && pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_example_connector.py --ignore=v1/kv_connector/unit/test_lmcache_integration.py --ignore=v1/kv_connector/unit/test_hf3fs_client.py --ignore=v1/kv_connector/unit/test_hf3fs_connector.py --ignore=v1/kv_connector/unit/test_hf3fs_metadata_server.py --ignore=v1/kv_connector/unit/test_offloading_connector.py' - label: "XPU server test" depends_on: diff --git a/docker/Dockerfile.xpu b/docker/Dockerfile.xpu index 529388f0c6..ed8a347005 100644 --- a/docker/Dockerfile.xpu +++ b/docker/Dockerfile.xpu @@ -75,13 +75,13 @@ RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRO # Install UMD RUN mkdir neo && \ cd neo && \ - wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.24.8/intel-igc-core-2_2.24.8+20344_amd64.deb && \ - wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.24.8/intel-igc-opencl-2_2.24.8+20344_amd64.deb && \ - wget https://github.com/intel/compute-runtime/releases/download/25.48.36300.8/intel-ocloc_25.48.36300.8-0_amd64.deb && \ - wget https://github.com/intel/compute-runtime/releases/download/25.48.36300.8/intel-opencl-icd_25.48.36300.8-0_amd64.deb && \ - wget https://github.com/intel/compute-runtime/releases/download/25.48.36300.8/libigdgmm12_22.8.2_amd64.deb && \ - wget https://github.com/intel/compute-runtime/releases/download/25.48.36300.8/libze-intel-gpu1_25.48.36300.8-0_amd64.deb && \ - wget https://github.com/oneapi-src/level-zero/releases/download/v1.26.0/level-zero_1.26.0+u24.04_amd64.deb && \ + wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.34.4/intel-igc-core-2_2.34.4+21428_amd64.deb && \ + wget https://github.com/intel/intel-graphics-compiler/releases/download/v2.34.4/intel-igc-opencl-2_2.34.4+21428_amd64.deb && \ + wget https://github.com/intel/compute-runtime/releases/download/26.18.38308.1/intel-ocloc_26.18.38308.1-0_amd64.deb && \ + wget https://github.com/intel/compute-runtime/releases/download/26.18.38308.1/intel-opencl-icd_26.18.38308.1-0_amd64.deb && \ + wget https://github.com/intel/compute-runtime/releases/download/26.18.38308.1/libigdgmm12_22.10.0_amd64.deb && \ + wget https://github.com/intel/compute-runtime/releases/download/26.18.38308.1/libze-intel-gpu1_26.18.38308.1-0_amd64.deb && \ + wget https://github.com/oneapi-src/level-zero/releases/download/v1.28.2/level-zero_1.28.2+u24.04_amd64.deb && \ dpkg -i *.deb && \ cd .. && \ rm -rf neo diff --git a/docs/getting_started/installation/gpu.xpu.inc.md b/docs/getting_started/installation/gpu.xpu.inc.md index f22f515947..8564f2a726 100644 --- a/docs/getting_started/installation/gpu.xpu.inc.md +++ b/docs/getting_started/installation/gpu.xpu.inc.md @@ -27,6 +27,7 @@ Currently, there are no pre-built XPU wheels. - First, install required [driver](https://dgpu-docs.intel.com/driver/installation.html#installing-gpu-drivers). - Second, install Python packages for vLLM XPU backend building (Intel OneAPI dependencies are installed automatically as part of `torch-xpu`, see [PyTorch XPU get started](https://docs.pytorch.org/docs/stable/notes/get_start_xpu.html)): +- Start from vllm-xpu-kernels v0.1.10, we recommend user upgrade driver to [compute runtime 26.18](https://github.com/intel/compute-runtime/releases/tag/26.14.37833.4) release, to avoid potential compatibility issue. ```bash git clone https://github.com/vllm-project/vllm.git diff --git a/requirements/xpu.txt b/requirements/xpu.txt index f17e2281f7..a24ac9ae53 100644 --- a/requirements/xpu.txt +++ b/requirements/xpu.txt @@ -17,4 +17,4 @@ torchaudio torchvision auto_round_lib>=0.13.3 -vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.9.1/vllm_xpu_kernels-0.1.9.1-cp38-abi3-manylinux_2_28_x86_64.whl +vllm_xpu_kernels @ https://github.com/vllm-project/vllm-xpu-kernels/releases/download/v0.1.10/vllm_xpu_kernels-0.1.10-cp38-abi3-manylinux_2_28_x86_64.whl