vllm-ascend 0.11.0rc1__tar.gz → 0.11.0rc3__tar.gz

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/_accuracy_test.yaml

@@ -30,7 +30,7 @@ jobs:
     runs-on: ${{ inputs.runner }}
     name: ${{ inputs.model_name }} accuracy
     container:
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
       env:
         VLLM_USE_MODELSCOPE: True
         # 1. If version specified (work_dispatch), do specified branch accuracy test

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/_e2e_test.yaml

@@ -106,8 +106,8 @@ jobs:
           # ------------------------------------ v1 spec decode test ------------------------------------ #
           pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py
           pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_torchair_correctness.py
-          # Fix me: OOM error
-          #pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py
+          # Fix me: test_eagle_correctness OOM error
+          pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_spec_decode.py
 
           pytest -sv tests/e2e/singlecard/ops/
 

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/accuracy_test.yaml

@@ -68,5 +68,5 @@ jobs:
     with:
       vllm: v0.11.0
       runner:  linux-aarch64-${{ matrix.runner }}
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
       model_name: ${{ matrix.model_name }}

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/multi_node_test.yaml

@@ -23,7 +23,7 @@ jobs:
     # This is a runner with no NPU for k8s controller
     runs-on: linux-aarch64-a3-0
     container:
-      image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11
+      image: m.daocloud.io/quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
       env:
         KUBECONFIG: /tmp/kubeconfig
         KUBECTL: /root/.cache/.kube/kubectl

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/nightly_benchmarks.yaml

@@ -56,7 +56,7 @@ jobs:
             vllm_use_v1: 1
       max-parallel: 1
     container:
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
       volumes:
         - /usr/local/dcmi:/usr/local/dcmi
         - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/release_whl.yml

@@ -57,7 +57,13 @@ jobs:
     - name: Print
       run: |
         lscpu
-        
+
+    - name: Free up disk space
+      uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
+      with:
+        tool-cache: true
+        docker-images: false
+
     - name: Build wheel
       run: |
         ls

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/vllm_ascend_dist.yaml

@@ -47,7 +47,7 @@ jobs:
     name: vLLM Ascend test
     runs-on: ${{ matrix.os }}
     container:
-      image: m.daocloud.io/quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11
+      image: m.daocloud.io/quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
       env:
         DEBIAN_FRONTEND: noninteractive
     steps:
@@ -97,4 +97,4 @@ jobs:
           VLLM_USE_MODELSCOPE: True
         run: |
           # TODO: enable more tests
-          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe
+          pytest -sv tests/e2e/multicard/test_offline_inference_distributed.py::test_models_distributed_DeepSeek_multistream_moe

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/vllm_ascend_test.yaml

@@ -145,5 +145,5 @@ jobs:
     with:
       vllm: ${{ matrix.vllm_version }}
       runner: linux-aarch64-a2
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
       type: light

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/vllm_ascend_test_310p.yaml

@@ -58,7 +58,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     container:
       # TODO(yikun): Remove m.daocloud.io prefix when infra proxy ready
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-310p-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-310p-ubuntu22.04-py3.11
       env:
         VLLM_LOGGING_LEVEL: ERROR
         VLLM_USE_MODELSCOPE: True

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/vllm_ascend_test_full.yaml

@@ -76,5 +76,5 @@ jobs:
     with:
       vllm: ${{ matrix.vllm_version }}
       runner: linux-aarch64-a2
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
       type: full

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/vllm_ascend_test_full_vllm_main.yaml

@@ -41,5 +41,5 @@ jobs:
     with:
       vllm: main
       runner: linux-aarch64-a2
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
       type: full

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/vllm_ascend_test_models.yaml

@@ -79,7 +79,7 @@ jobs:
     with:
       vllm: v0.11.0
       runner:  linux-aarch64-${{ matrix.runner }}
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
       model_name: ${{ matrix.model_name }}
       upload: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.vllm-ascend-version == 'latest' }}
 

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/.github/workflows/vllm_ascend_test_pd.yaml

@@ -49,7 +49,7 @@ jobs:
     runs-on: linux-arm64-npu-static-8
 
     container:
-      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+      image: swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11
       volumes:
         - /usr/local/dcmi:/usr/local/dcmi
         - /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
@@ -109,4 +109,4 @@ jobs:
       - name: Run vllm-project/vllm-ascend PD Disaggregation edge test
         run: |
           git config --global --add safe.directory/__w/vllm-ascend/vllm-ascend
-          bash tests/e2e/pd_disaggreate/run_edge_case_test.sh
+          bash tests/e2e/pd_disaggreate/run_edge_case_test.sh

vllm_ascend-0.11.0rc1/Dockerfile.a3 → vllm_ascend-0.11.0rc3/Dockerfile

@@ -15,24 +15,33 @@
 # This file is a part of the vllm-ascend project.
 #
 
-FROM quay.io/ascend/cann:8.3.rc1-a3-ubuntu22.04-py3.11
+FROM quay.io/ascend/cann:8.3.rc2-910b-ubuntu22.04-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1
+ARG MOONCAKE_TAG="v0.3.7.post2"
 
 # Define environments
 ENV DEBIAN_FRONTEND=noninteractive
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
 
-RUN apt-get update -y && \
-    apt-get install -y python3-pip git vim wget net-tools gcc g++ cmake libnuma-dev && \
-    rm -rf /var/cache/apt/* && \
-    rm -rf /var/lib/apt/lists/*
-
 WORKDIR /workspace
 
 COPY . /vllm-workspace/vllm-ascend/
 
+# Install Mooncake dependencies
+RUN apt-get update -y && \
+    apt-get install -y git vim wget net-tools gcc g++ cmake libnuma-dev && \
+    git clone --depth 1 --branch ${MOONCAKE_TAG} https://github.com/kvcache-ai/Mooncake /vllm-workspace/Mooncake && \
+    cp /vllm-workspace/vllm-ascend/tools/mooncake_installer.sh /vllm-workspace/Mooncake/ && \
+    cd /vllm-workspace/Mooncake && bash mooncake_installer.sh -y && \
+    export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/lib64 && \
+    mkdir -p build && cd build && cmake .. -DUSE_ASCEND_DIRECT=ON && \
+    make -j$(nproc) && make install && \
+    rm -fr /vllm-workspace/Mooncake/build && \
+    rm -rf /var/cache/apt/* && \
+    rm -rf /var/lib/apt/lists/*
+
 RUN pip config set global.index-url ${PIP_INDEX_URL}
 
 # Install vLLM
@@ -40,7 +49,7 @@ ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
 ARG VLLM_TAG=v0.11.0
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
-RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
     python3 -m pip cache purge
 
@@ -54,7 +63,7 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
     python3 -m pip cache purge
 
 # Install modelscope (for fast download) and ray (for multinode)
-RUN python3 -m pip install modelscope 'ray>=2.47.1' 'protobuf>3.20.0' && \
+RUN python3 -m pip install modelscope 'ray>=2.47.1,<=2.48.0' 'protobuf>3.20.0' && \
     python3 -m pip cache purge
 
-CMD ["/bin/bash"]
+CMD ["/bin/bash"]

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/Dockerfile.310p

@@ -15,7 +15,7 @@
 # This file is a part of the vllm-ascend project.
 #
 
-FROM quay.io/ascend/cann:8.3.rc1-310p-ubuntu22.04-py3.11
+FROM quay.io/ascend/cann:8.3.rc2-310p-ubuntu22.04-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1
@@ -40,7 +40,7 @@ ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
 ARG VLLM_TAG=v0.11.0
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
-RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
     python3 -m pip cache purge
 

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/Dockerfile.310p.openEuler

@@ -15,7 +15,7 @@
 # This file is a part of the vllm-ascend project.
 #
 
-FROM quay.io/ascend/cann:8.3.rc1-310p-openeuler24.03-py3.11
+FROM quay.io/ascend/cann:8.3.rc2-310p-openeuler24.03-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1
@@ -38,7 +38,7 @@ ARG VLLM_TAG=v0.11.0
 
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
-RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
     python3 -m pip cache purge
 

vllm_ascend-0.11.0rc1/Dockerfile → vllm_ascend-0.11.0rc3/Dockerfile.a3

@@ -15,32 +15,40 @@
 # This file is a part of the vllm-ascend project.
 #
 
-FROM quay.io/ascend/cann:8.3.rc1-910b-ubuntu22.04-py3.11
+FROM quay.io/ascend/cann:8.3.rc2-a3-ubuntu22.04-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1
+ARG MOONCAKE_TAG=v0.3.7.post2
 
+COPY . /vllm-workspace/vllm-ascend/
 # Define environments
 ENV DEBIAN_FRONTEND=noninteractive
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
 
-RUN apt-get update -y && \
-    apt-get install -y python3-pip git vim wget net-tools gcc g++ cmake libnuma-dev && \
-    rm -rf /var/cache/apt/* && \
-    rm -rf /var/lib/apt/lists/*
+RUN pip config set global.index-url ${PIP_INDEX_URL}
 
 WORKDIR /workspace
 
-COPY . /vllm-workspace/vllm-ascend/
-
-RUN pip config set global.index-url ${PIP_INDEX_URL}
+# Install Mooncake dependencies
+RUN apt-get update -y && \
+    apt-get install -y git vim wget net-tools gcc g++ cmake libnuma-dev && \
+    git clone --depth 1 --branch ${MOONCAKE_TAG} https://github.com/kvcache-ai/Mooncake /vllm-workspace/Mooncake && \
+    cp /vllm-workspace/vllm-ascend/tools/mooncake_installer.sh /vllm-workspace/Mooncake/ && \
+    cd /vllm-workspace/Mooncake && bash mooncake_installer.sh -y && \
+    export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/lib64 && \
+    mkdir -p build && cd build && cmake .. -DUSE_ASCEND_DIRECT=ON && \
+    make -j$(nproc) && make install && \
+    rm -fr /vllm-workspace/Mooncake/build && \
+    rm -rf /var/cache/apt/* && \
+    rm -rf /var/lib/apt/lists/*
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
 ARG VLLM_TAG=v0.11.0
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
-RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
     python3 -m pip cache purge
 
@@ -54,7 +62,7 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
     python3 -m pip cache purge
 
 # Install modelscope (for fast download) and ray (for multinode)
-RUN python3 -m pip install modelscope 'ray>=2.47.1' 'protobuf>3.20.0' && \
+RUN python3 -m pip install modelscope 'ray>=2.47.1,<=2.48.0' 'protobuf>3.20.0' && \
     python3 -m pip cache purge
 
 CMD ["/bin/bash"]

vllm_ascend-0.11.0rc1/Dockerfile.openEuler → vllm_ascend-0.11.0rc3/Dockerfile.a3.openEuler

@@ -15,30 +15,43 @@
 # This file is a part of the vllm-ascend project.
 #
 
-FROM quay.io/ascend/cann:8.3.rc1-910b-openeuler24.03-py3.11
+FROM quay.io/ascend/cann:8.3.rc2-a3-openeuler24.03-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1
+ARG MOONCAKE_TAG="v0.3.7.post2"
 
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
 
-RUN yum update -y && \
-    yum install -y python3-pip git vim wget net-tools gcc gcc-c++ make cmake numactl-devel && \
-    rm -rf /var/cache/yum
-
 RUN pip config set global.index-url ${PIP_INDEX_URL}
 
 WORKDIR /workspace
 
 COPY . /vllm-workspace/vllm-ascend/
 
+SHELL ["/bin/bash", "-c"]
+
+RUN yum update -y && \
+    yum install -y git vim wget net-tools gcc gcc-c++ make cmake numactl-devel && \
+    git clone --depth 1 --branch ${MOONCAKE_TAG} https://github.com/kvcache-ai/Mooncake /vllm-workspace/Mooncake && \
+    cp /vllm-workspace/vllm-ascend/tools/mooncake_installer.sh /vllm-workspace/Mooncake/ && \
+    ARCH=$(uname -m) && \
+    source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
+    export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/${ARCH}-linux/devlib:/usr/local/Ascend/ascend-toolkit/latest/${ARCH}-linux/lib64:$LD_LIBRARY_PATH && \
+    export CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:/usr/include/c++/12:/usr/include/c++/12/${ARCH}-openEuler-linux && \
+    cd /vllm-workspace/Mooncake && \
+    bash mooncake_installer.sh -y && \
+    mkdir -p build && cd build && cmake .. -DUSE_ASCEND_DIRECT=ON && \
+    make -j$(nproc) && make install && \
+    rm -fr /vllm-workspace/Mooncake/build && \
+    rm -rf /var/cache/yum/*
+
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
 ARG VLLM_TAG=v0.11.0
-
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
-RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
     python3 -m pip cache purge
 
@@ -52,7 +65,7 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
     python3 -m pip cache purge
 
 # Install modelscope (for fast download) and ray (for multinode)
-RUN python3 -m pip install modelscope 'ray>=2.47.1' 'protobuf>3.20.0' && \
+RUN python3 -m pip install modelscope 'ray>=2.47.1,<=2.48.0' 'protobuf>3.20.0' && \
     python3 -m pip cache purge
 
 CMD ["/bin/bash"]

vllm_ascend-0.11.0rc1/Dockerfile.a3.openEuler → vllm_ascend-0.11.0rc3/Dockerfile.openEuler

@@ -15,16 +15,14 @@
 # This file is a part of the vllm-ascend project.
 #
 
-FROM quay.io/ascend/cann:8.3.rc1-a3-openeuler24.03-py3.11
+FROM quay.io/ascend/cann:8.3.rc2-910b-openeuler24.03-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1
+ARG MOONCAKE_TAG="v0.3.7.post2"
 
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
 
-RUN yum update -y && \
-    yum install -y python3-pip git vim wget net-tools gcc gcc-c++ make cmake numactl-devel && \
-    rm -rf /var/cache/yum
 
 RUN pip config set global.index-url ${PIP_INDEX_URL}
 
@@ -32,13 +30,29 @@ WORKDIR /workspace
 
 COPY . /vllm-workspace/vllm-ascend/
 
+SHELL ["/bin/bash", "-c"]
+
+RUN yum update -y && \
+    yum install -y git vim wget net-tools gcc gcc-c++ make cmake numactl-devel && \
+    git clone --depth 1 --branch ${MOONCAKE_TAG} https://github.com/kvcache-ai/Mooncake /vllm-workspace/Mooncake && \
+    cp /vllm-workspace/vllm-ascend/tools/mooncake_installer.sh /vllm-workspace/Mooncake/ && \
+    ARCH=$(uname -m) && \
+    source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
+    export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/${ARCH}-linux/devlib:/usr/local/Ascend/ascend-toolkit/latest/${ARCH}-linux/lib64:$LD_LIBRARY_PATH && \
+    export CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:/usr/include/c++/12:/usr/include/c++/12/${ARCH}-openEuler-linux && \
+    cd /vllm-workspace/Mooncake && \
+    bash mooncake_installer.sh -y && \
+    mkdir -p build && cd build && cmake .. -DUSE_ASCEND_DIRECT=ON && \
+    make -j$(nproc) && make install && \
+    rm -fr /vllm-workspace/Mooncake/build && \
+    rm -rf /var/cache/yum/*
+
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=v0.11.0
-
+ARG VLLM_TAG=v0.11.2
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
-RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
+RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
     python3 -m pip uninstall -y triton && \
     python3 -m pip cache purge
 
@@ -52,7 +66,7 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
     python3 -m pip cache purge
 
 # Install modelscope (for fast download) and ray (for multinode)
-RUN python3 -m pip install modelscope 'ray>=2.47.1' 'protobuf>3.20.0' && \
+RUN python3 -m pip install modelscope 'ray>=2.47.1,<=2.48.0' 'protobuf>3.20.0' && \
     python3 -m pip cache purge
 
-CMD ["/bin/bash"]
+CMD ["/bin/bash"]

{vllm_ascend-0.11.0rc1/vllm_ascend.egg-info → vllm_ascend-0.11.0rc3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vllm_ascend
-Version: 0.11.0rc1
+Version: 0.11.0rc3
 Summary: vLLM Ascend backend plugin
 Home-page: https://github.com/vllm-project/vllm-ascend
 Author: vLLM-Ascend team
@@ -37,6 +37,7 @@ Requires-Dist: msgpack
 Requires-Dist: quart
 Requires-Dist: numba
 Requires-Dist: torch-npu==2.7.1
+Requires-Dist: transformers<=4.57.1
 Dynamic: author
 Dynamic: classifier
 Dynamic: description

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/docs/source/conf.py

@@ -75,7 +75,7 @@ myst_substitutions = {
     'pip_vllm_ascend_version': "0.11.0rc0",
     'pip_vllm_version': "0.11.0",
     # CANN image tag
-    'cann_image_tag': "8.3.rc1-910b-ubuntu22.04-py3.11",
+    'cann_image_tag': "8.3.rc2-910b-ubuntu22.04-py3.11",
     # vllm version in ci
     'ci_vllm_version': 'v0.11.0rc3',
 }

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/docs/source/installation.md

@@ -79,19 +79,19 @@ source vllm-ascend-env/bin/activate
 pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple attrs 'numpy<2.0.0' decorator sympy cffi pyyaml pathlib2 psutil protobuf scipy requests absl-py wheel typing_extensions
 
 # Download and install the CANN package.
-wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC1/Ascend-cann-toolkit_8.3.RC1_linux-"$(uname -i)".run
-chmod +x ./Ascend-cann-toolkit_8.3.RC1_linux-"$(uname -i)".run
-./Ascend-cann-toolkit_8.3.RC1_linux-"$(uname -i)".run --full
-# https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C22B800TP052/Ascend-cann-kernels-910b_8.3.rc1_linux-aarch64.run
+wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run
+chmod +x ./Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run
+./Ascend-cann-toolkit_8.3.RC2_linux-"$(uname -i)".run --full
+# https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/Milan-ASL/Milan-ASL%20V100R001C22B800TP052/Ascend-cann-kernels-910b_8.3.rc2_linux-aarch64.run
 
 source /usr/local/Ascend/ascend-toolkit/set_env.sh
-wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC1/Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run
-chmod +x ./Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run
-./Ascend-cann-kernels-910b_8.3.RC1_linux-"$(uname -i)".run --install
+wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run
+chmod +x ./Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run
+./Ascend-cann-kernels-910b_8.3.RC2_linux-"$(uname -i)".run --install
 
-wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC1/Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run
-chmod +x ./Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run
-./Ascend-cann-nnal_8.3.RC1_linux-"$(uname -i)".run --install
+wget --header="Referer: https://www.hiascend.com/" https://ascend-repo.obs.cn-east-2.myhuaweicloud.com/CANN/CANN%208.3.RC2/Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run
+chmod +x ./Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run
+./Ascend-cann-nnal_8.3.RC2_linux-"$(uname -i)".run --install
 
 source /usr/local/Ascend/nnal/atb/set_env.sh
 ```

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/docs/source/tutorials/index.md

@@ -8,6 +8,7 @@ single_npu_multimodal
 single_npu_audio
 single_npu_qwen3_embedding
 single_npu_qwen3_quantization
+single_node_pd_disaggregation_llmdatadist
 multi_npu_qwen3_next
 multi_npu
 multi_npu_moge

{vllm_ascend-0.11.0rc1 → vllm_ascend-0.11.0rc3}/docs/source/tutorials/multi_npu_qwen3_next.md

@@ -51,7 +51,7 @@ Install the Ascend BiSheng toolkit:
 wget https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/Ascend-BiSheng-toolkit_aarch64.run
 chmod a+x Ascend-BiSheng-toolkit_aarch64.run
 ./Ascend-BiSheng-toolkit_aarch64.run --install
-source /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
+source /usr/local/Ascend/8.3.RC2/bisheng_toolkit/set_env.sh
 ```
 
 Install Triton Ascend:
@@ -75,7 +75,7 @@ Coming soon ...
 Please make sure you have already executed the command:
 
 ```bash
-source /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
+source /usr/local/Ascend/8.3.RC2/bisheng_toolkit/set_env.sh
 ```
 
 :::::{tab-set}