add deepseek-r1-w8a8 tutorial.

.github/Dockerfile.buildwheel

@@ -15,7 +15,7 @@
 # This file is a part of the vllm-ascend project.
 #
 ARG PY_VERSION=3.11
-FROM quay.io/ascend/manylinux:8.3.rc1-910b-manylinux_2_28-py${PY_VERSION}
+FROM quay.io/ascend/manylinux:8.3.rc2-910b-manylinux_2_28-py${PY_VERSION}
 
 ARG COMPILE_CUSTOM_KERNELS=1
 ARG SOC_VERSION

.github/workflows/_e2e_nightly_multi_node.yaml

@@ -15,7 +15,7 @@ on:
         required: false
         type: string
         description: base image for pods
-        default: "swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11"
+        default: "swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11"
       config_file_path:
         required: true
         type: string
@@ -69,7 +69,7 @@ jobs:
     # This is the runner with no NPU for k8s controller
     runs-on: ${{ inputs.runner }}
     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

.github/workflows/_e2e_nightly_single_node.yaml

@@ -29,7 +29,7 @@ on:
       image:
         required: false
         type: string
-        default: "swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc1-910b-ubuntu22.04-py3.11"
+        default: "swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.3.rc2-910b-ubuntu22.04-py3.11"
       tests:
         required: true
         type: string

.github/workflows/_e2e_nightly_single_node_models.yaml

@@ -59,7 +59,7 @@ jobs:
     name: ${{inputs.model_list}} accuracy test
     runs-on: ${{ inputs.runner }}
     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
         GHA_VLLM_ASCEND_VERSION: ${{ inputs.vllm-ascend }}
@@ -108,10 +108,7 @@ jobs:
         if: ${{ inputs.runner == 'linux-aarch64-a2-4' && contains(inputs.model_list, 'Qwen3-Next-80B-A3B-Instruct') }}
         shell: bash -l {0}
         run: |
-          wget -q https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/Ascend-BiSheng-toolkit_aarch64.run -O /tmp/Ascend-BiSheng-toolkit_aarch64.run
-          chmod a+x /tmp/Ascend-BiSheng-toolkit_aarch64.run
-          /tmp/Ascend-BiSheng-toolkit_aarch64.run --install
-          . /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
+          . /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
           python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20250914-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
 
       - name: Resolve vllm-ascend version
@@ -225,4 +222,4 @@ jobs:
           path: ./benchmarks/accuracy/
           if-no-files-found: warn
           retention-days: 90
-          overwrite: true
+          overwrite: true

.github/workflows/_e2e_test.yaml

@@ -179,6 +179,7 @@ jobs:
           VLLM_USE_MODELSCOPE: True
         if: ${{ inputs.type == 'full' }}
         run: |
+          pytest -sv tests/e2e/multicard/test_quantization.py
           pytest -sv tests/e2e/multicard/test_aclgraph_capture_replay.py
           pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py
           pytest -sv tests/e2e/multicard/test_full_graph_mode.py
@@ -211,7 +212,7 @@ jobs:
     if: ${{ needs.e2e.result == 'success' && needs.e2e-2-cards.result == 'success' && inputs.type == 'full' }}
     runs-on: linux-aarch64-a3-4
     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:
         VLLM_LOGGING_LEVEL: ERROR
         VLLM_USE_MODELSCOPE: True
@@ -274,11 +275,8 @@ jobs:
       - name: Install Ascend toolkit & triton_ascend (for Qwen3-Next-80B-A3B-Instruct)
         shell: bash -l {0}
         run: |
-          wget -q https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/Ascend-BiSheng-toolkit_aarch64.run -O /tmp/Ascend-BiSheng-toolkit_aarch64.run
-          chmod a+x /tmp/Ascend-BiSheng-toolkit_aarch64.run
-          /tmp/Ascend-BiSheng-toolkit_aarch64.run --install
-          . /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
-          python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev20250914-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl"
+          . /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
+          python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/triton_ascend-3.2.0.dev2025110717-cp311-cp311-manylinux_2_27.whl"
 
       - name: Run vllm-project/vllm-ascend Qwen3 Next test
         working-directory: ./vllm-ascend
@@ -287,5 +285,5 @@ jobs:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
           VLLM_USE_MODELSCOPE: True
         run: |
-          . /usr/local/Ascend/8.3.RC1/bisheng_toolkit/set_env.sh
+          . /usr/local/Ascend/ascend-toolkit/8.3.RC2/bisheng_toolkit/set_env.sh
           pytest -sv tests/e2e/multicard/test_qwen3_next.py

.github/workflows/_nightly_image_build.yaml

@@ -45,7 +45,7 @@ jobs:
             --network host \
             --platform linux/arm64 \
             -f .github/Dockerfile.nightly.${TARGET} \
-            --build-arg CANN_VERSION="8.3.rc1" \
+            --build-arg CANN_VERSION="8.3.rc2" \
             --build-arg UBUNTU_VERSION="22.04" \
             --build-arg PYTHON_VERSION="3.11" \
             -t "$IMAGE_TAG" .

.github/workflows/nightly_benchmarks.yaml

@@ -55,7 +55,7 @@ jobs:
             vllm_ascend_branch: main
       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

.github/workflows/release_whl.yml

@@ -96,8 +96,14 @@ jobs:
           --exclude libge_common_base.so \
           --exclude libc10.so \
           --exclude libc_sec.so \
+          --exclude libnnopbase.so \
+          --exclude libprofapi.so \
+          --exclude libgraph_base.so \
+          --exclude libgraph.so \
+          --exclude libexe_graph.so \
           --exclude "libascend*.so" \
           --exclude "libtorch*.so" \
+          --exclude "libopapi.so" \
           --exclude "liberror_manager.so"
         done
         rm -f dist/*.whl

.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

.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

.github/workflows/vllm_ascend_test_pr_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

.github/workflows/vllm_ascend_test_pr_light.yaml

@@ -76,8 +76,8 @@ jobs:
     if: ${{ needs.lint.result == 'success' && (needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.ut_tracker == 'true') }}
     runs-on: ubuntu-latest
     container:
-      # fixme: vllm-ascend install failed with 8.3.rc1 on github action
-      image: quay.io/ascend/cann:8.2.rc1-910b-ubuntu22.04-py3.11
+      # fixme: vllm-ascend install failed with 8.3.rc2 on github action
+      image: quay.io/ascend/cann:8.2.rc2-910b-ubuntu22.04-py3.11
       env:
         VLLM_LOGGING_LEVEL: ERROR
         VLLM_USE_MODELSCOPE: True
@@ -151,5 +151,5 @@ 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

.github/workflows/vllm_ascend_test_report.yaml

@@ -74,7 +74,7 @@ jobs:
     with:
       vllm: v0.11.2
       runner: ${{ 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_list: ${{ toJson(matrix.model_list) }}
       upload: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.vllm-ascend-version == 'latest' }}
 

.pre-commit-config.yaml

@@ -12,7 +12,7 @@ repos:
     - id: codespell
       args: [
         --toml, pyproject.toml,
-        '--skip', 'tests/e2e/multicard/test_torchair_graph_mode.py,csrc/mla_preprocess/**,tests/prompts/**,./benchmarks/sonnet.txt,*tests/lora/data/**,build/**,./vllm_ascend.egg-info/**,.github/**,typos.toml',
+        '--skip', 'tests/e2e/multicard/test_torchair_graph_mode.py,csrc/**,tests/prompts/**,./benchmarks/sonnet.txt,*tests/lora/data/**,build/**,./vllm_ascend.egg-info/**,.github/**,typos.toml',
         '-L', 'CANN,cann,NNAL,nnal,ASCEND,ascend,EnQue,CopyIn,ArchType,AND'
       ]
       additional_dependencies:
@@ -37,7 +37,7 @@ repos:
   - id: typos
     args: [
       "--force-exclude",
-      "--exclude", "csrc/mla_preprocess/**"
+      "--exclude", "csrc/**"
     ]
 - repo: https://github.com/PyCQA/isort
   rev: 6.0.1

CMakeLists.txt

@@ -63,7 +63,8 @@ ascendc_library(vllm_ascend_kernels SHARED
 message("TORCH_NPU_PATH is ${TORCH_NPU_PATH}")
 
 file(GLOB VLLM_ASCEND_SRC
-${CMAKE_CURRENT_SOURCE_DIR}/csrc/*.cpp)
+${CMAKE_CURRENT_SOURCE_DIR}/csrc/*.cpp
+${CMAKE_CURRENT_SOURCE_DIR}/csrc/aclnn_torch_adapter/*.cpp)
 
 include_directories(
   ${pybind11_INCLUDE_DIRS}
@@ -81,13 +82,15 @@ set(
   ${TORCH_NPU_INCLUDE_DIRS}
   ${ASCEND_HOME_PATH}/include
   ${ASCEND_HOME_PATH}/aarch64-linux/include/experiment/platform
+  ${ASCEND_HOME_PATH}/x86_64-linux/include/experiment/platform
 )
 
 pybind11_add_module(vllm_ascend_C ${VLLM_ASCEND_SRC})
 
 target_link_directories(
   vllm_ascend_C
   PRIVATE
+  ${TORCH_LIBRARY_DIRS}
   ${TORCH_NPU_PATH}/lib/
   ${ASCEND_HOME_PATH}/lib64
 )
@@ -96,14 +99,15 @@ target_link_libraries(
   vllm_ascend_C
   PUBLIC
   ${TORCH_LIBRARIES}
-  libtorch_npu.so
+  torch_npu
   vllm_ascend_kernels
   ascendcl
   tiling_api
   register
   platform
   ascendalog
   dl
+  opapi
 )
 
 target_link_options(vllm_ascend_C PRIVATE "-Wl,-rpath,$ORIGIN:$ORIGIN/lib")

Dockerfile

@@ -15,7 +15,7 @@
 # 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.rc2-910b-ubuntu22.04-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1

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

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

Dockerfile.a3

@@ -15,7 +15,7 @@
 # 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-a3-ubuntu22.04-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1

Dockerfile.a3.openEuler

@@ -15,7 +15,7 @@
 # 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-a3-openeuler24.03-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1

Dockerfile.openEuler

@@ -15,7 +15,7 @@
 # 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.rc2-910b-openeuler24.03-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1