[v0.18.0][Triton] Fix triton-ascend version in Dockerfile (#7766)

### What this PR does / why we need it?
Triton-ascend occasionally encounters compilation errors, which is a
known issue in triton-ascend 3.2.0. However, we want to use the official
version rather than the development version, so we only changed the
triton-ascend version in the Dockerfile and added a FAQ to explain this
issue.

---------

Signed-off-by: MengqingCao <cmq0113@163.com>

Dockerfile

@@ -66,6 +66,10 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
     export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
     python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
     if [ "$(uname -i)" = "x86_64" ]; then python3 -m pip uninstall -y triton; fi && \
+    PYTHON_TAG=$(python3 -c "import sys; print(f'cp{sys.version_info.major}{sys.version_info.minor}')") && \
+    ARCH=$(python3 -c "import platform; machine = platform.machine().lower(); arch_map = {'x86_64': 'x86_64', 'amd64': 'x86_64', 'aarch64': 'aarch64', 'arm64': 'aarch64'}; print(arch_map.get(machine, machine))") && \
+    TRITON_ASCEND_WHEEL="triton_ascend-3.2.0.dev20260322-${PYTHON_TAG}-${PYTHON_TAG}-manylinux_2_27_${ARCH}.manylinux_2_28_${ARCH}.whl" && \
+    python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${TRITON_ASCEND_WHEEL}" && \
     python3 -m pip cache purge
 
 # Install clang-15 (for triton-ascend)

Dockerfile.a3

@@ -65,6 +65,10 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
     export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
     python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
     if [ "$(uname -i)" = "x86_64" ]; then python3 -m pip uninstall -y triton; fi && \
+    PYTHON_TAG=$(python3 -c "import sys; print(f'cp{sys.version_info.major}{sys.version_info.minor}')") && \
+    ARCH=$(python3 -c "import platform; machine = platform.machine().lower(); arch_map = {'x86_64': 'x86_64', 'amd64': 'x86_64', 'aarch64': 'aarch64', 'arm64': 'aarch64'}; print(arch_map.get(machine, machine))") && \
+    TRITON_ASCEND_WHEEL="triton_ascend-3.2.0.dev20260322-${PYTHON_TAG}-${PYTHON_TAG}-manylinux_2_27_${ARCH}.manylinux_2_28_${ARCH}.whl" && \
+    python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${TRITON_ASCEND_WHEEL}" && \
     python3 -m pip cache purge
 
 # Install clang-15 (for triton-ascend)

Dockerfile.a3.openEuler

@@ -66,6 +66,10 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
     export CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:/usr/include/c++/12:/usr/include/c++/12/`uname -i`-openEuler-linux && \
     python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
     if [ "$(uname -i)" = "x86_64" ]; then python3 -m pip uninstall -y triton; fi && \
+    PYTHON_TAG=$(python3 -c "import sys; print(f'cp{sys.version_info.major}{sys.version_info.minor}')") && \
+    ARCH=$(python3 -c "import platform; machine = platform.machine().lower(); arch_map = {'x86_64': 'x86_64', 'amd64': 'x86_64', 'aarch64': 'aarch64', 'arm64': 'aarch64'}; print(arch_map.get(machine, machine))") && \
+    TRITON_ASCEND_WHEEL="triton_ascend-3.2.0.dev20260322-${PYTHON_TAG}-${PYTHON_TAG}-manylinux_2_27_${ARCH}.manylinux_2_28_${ARCH}.whl" && \
+    python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${TRITON_ASCEND_WHEEL}" && \
     python3 -m pip cache purge
 
 # Install clang (for triton-ascend)

Dockerfile.openEuler

@@ -66,6 +66,10 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
     export CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:/usr/include/c++/12:/usr/include/c++/12/`uname -i`-openEuler-linux && \
     python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
     if [ "$(uname -i)" = "x86_64" ]; then python3 -m pip uninstall -y triton; fi && \
+    PYTHON_TAG=$(python3 -c "import sys; print(f'cp{sys.version_info.major}{sys.version_info.minor}')") && \
+    ARCH=$(python3 -c "import platform; machine = platform.machine().lower(); arch_map = {'x86_64': 'x86_64', 'amd64': 'x86_64', 'aarch64': 'aarch64', 'arm64': 'aarch64'}; print(arch_map.get(machine, machine))") && \
+    TRITON_ASCEND_WHEEL="triton_ascend-3.2.0.dev20260322-${PYTHON_TAG}-${PYTHON_TAG}-manylinux_2_27_${ARCH}.manylinux_2_28_${ARCH}.whl" && \
+    python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${TRITON_ASCEND_WHEEL}" && \
     python3 -m pip cache purge
 
 # Install clang (for triton-ascend)

docs/source/faqs.md

@@ -289,3 +289,14 @@ export SOC_VERSION="ascend310p1"
 # Atlas A5 (Ascend 950 series)
 export SOC_VERSION="<value starting with ascend950>"
 ```
+
+### 24. Compilation error occasionally encounters with triton-ascend
+
+As shown in [#7782](https://github.com/vllm-project/vllm-ascend/issues/7782), triton-ascend occasionally encounters compilation errors, which is a known issue in triton-ascend 3.2.0. To avoid this issue, please use the official docker images or install the specific triton-ascend version as following:
+
+```bash
+PYTHON_TAG=$(python3 -c "import sys; print(f'cp{sys.version_info.major}{sys.version_info.minor}')") && \
+ARCH=$(python3 -c "import platform; machine = platform.machine().lower(); arch_map = {'x86_64': 'x86_64', 'amd64': 'x86_64', 'aarch64': 'aarch64', 'arm64': 'aarch64'}; print(arch_map.get(machine, machine))") && \
+TRITON_ASCEND_WHEEL="triton_ascend-3.2.0.dev20260322-${PYTHON_TAG}-${PYTHON_TAG}-manylinux_2_27_${ARCH}.manylinux_2_28_${ARCH}.whl" && \
+python3 -m pip install "https://vllm-ascend.obs.cn-north-4.myhuaweicloud.com/vllm-ascend/${TRITON_ASCEND_WHEEL}"
+```