chip type judgement code optimization (#4485)

### What this PR does / why we need it?
| | cpu envir | npu envir |
|---|---|---|
| set `SOC_VERSION` | check if `SOC_VERSION` is in dict `soc_to_device`,
if not, raise an error that can not support current chip type. | print a
warning log when `SOC_VERSION` is not equal to chip type from `npu-smi`,
same as left for others. |
| not set `SOC_VERSION` | raise an error that `SOC_VERSION` is necessary
when compiling in a cpu envir. | use chip type from `npu-smi` to compile
vllm-ascend. |

### Does this PR introduce _any_ user-facing change?

Now we must set env `SOC_VERSION` when compiling in cpu envir. 

### How was this patch tested?


- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

Signed-off-by: zzzzwwjj <1183291235@qq.com>

.github/Dockerfile.buildwheel

@@ -18,10 +18,12 @@ ARG PY_VERSION=3.11
 FROM quay.io/ascend/manylinux:8.3.rc1-910b-manylinux_2_28-py${PY_VERSION}
 
 ARG COMPILE_CUSTOM_KERNELS=1
+ARG SOC_VERSION
 
 # Define environments
 ENV DEBIAN_FRONTEND=noninteractive
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
+ENV SOC_VERSION=$SOC_VERSION
 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

.github/workflows/image_310p_openeuler.yml

@@ -132,4 +132,5 @@ jobs:
         file: Dockerfile.310p.openEuler
         build-args: |
           PIP_INDEX_URL=https://pypi.org/simple
+          SOC_VERSION=ascend310p1
         provenance: false

.github/workflows/image_310p_ubuntu.yml

@@ -128,4 +128,5 @@ jobs:
         tags: ${{ steps.meta.outputs.tags }}
         build-args: |
           PIP_INDEX_URL=https://pypi.org/simple
+          SOC_VERSION=ascend310p1
         provenance: false

.github/workflows/image_a3_openeuler.yml

@@ -131,5 +131,6 @@ jobs:
         file: Dockerfile.a3.openEuler
         build-args: |
           PIP_INDEX_URL=https://pypi.org/simple
+          SOC_VERSION=ascend910_9391
         provenance: false
 

.github/workflows/image_a3_ubuntu.yml

@@ -127,5 +127,6 @@ jobs:
         tags: ${{ steps.meta.outputs.tags }}
         build-args: |
           PIP_INDEX_URL=https://pypi.org/simple
+          SOC_VERSION=ascend910_9391
         provenance: false
 

.github/workflows/image_openeuler.yml

@@ -131,4 +131,5 @@ jobs:
         file: Dockerfile.openEuler
         build-args: |
           PIP_INDEX_URL=https://pypi.org/simple
+          SOC_VERSION=ascend910b1
         provenance: false

.github/workflows/image_ubuntu.yml

@@ -128,4 +128,5 @@ jobs:
         tags: ${{ steps.meta.outputs.tags }}
         build-args: |
           PIP_INDEX_URL=https://pypi.org/simple
+          SOC_VERSION=ascend910b1
         provenance: false

.github/workflows/release_code.yml

@@ -59,6 +59,8 @@ jobs:
           python3 -m pip install twine setuptools_scm
 
       - name: Generate tar.gz
+        env:
+          SOC_VERSION: ascend910b1
         run: |
           python3 setup.py sdist
           ls dist

.github/workflows/release_whl.yml

@@ -69,6 +69,7 @@ jobs:
         ls
         docker build -f ./.github/Dockerfile.buildwheel \
         --build-arg PY_VERSION=${{ matrix.python-version }} \
+        --build-arg SOC_VERSION=ascend910b1 \
         -t wheel:v1 .
         docker run --rm \
         -u $(id -u):$(id -g) \

.github/workflows/vllm_ascend_test_pr_light.yaml

@@ -81,6 +81,7 @@ jobs:
       env:
         VLLM_LOGGING_LEVEL: ERROR
         VLLM_USE_MODELSCOPE: True
+        SOC_VERSION: ascend910b1
     strategy:
       matrix:
         vllm_version: [v0.11.2]

Dockerfile

@@ -20,10 +20,12 @@ FROM quay.io/ascend/cann:8.3.rc1-910b-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"
+ARG SOC_VERSION
 
 # Define environments
 ENV DEBIAN_FRONTEND=noninteractive
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
+ENV SOC_VERSION=$SOC_VERSION
 
 WORKDIR /workspace
 

Dockerfile.310p

@@ -19,10 +19,12 @@ FROM quay.io/ascend/cann:8.3.rc1-310p-ubuntu22.04-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1
+ARG SOC_VERSION
 
 # Define environments
 ENV DEBIAN_FRONTEND=noninteractive
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
+ENV SOC_VERSION=$SOC_VERSION
 
 RUN apt-get update -y && \
     apt-get install -y python3-pip git vim wget net-tools gcc g++ cmake libnuma-dev && \

Dockerfile.310p.openEuler

@@ -19,8 +19,10 @@ FROM quay.io/ascend/cann:8.3.rc1-310p-openeuler24.03-py3.11
 
 ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
 ARG COMPILE_CUSTOM_KERNELS=1
+ARG SOC_VERSION
 
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
+ENV SOC_VERSION=$SOC_VERSION
 
 RUN yum update -y && \
     yum install -y python3-pip git vim wget net-tools gcc gcc-c++ make cmake numactl-devel && \

Dockerfile.a3

@@ -20,11 +20,13 @@ FROM quay.io/ascend/cann:8.3.rc1-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
+ARG SOC_VERSION
 
 COPY . /vllm-workspace/vllm-ascend/
 # Define environments
 ENV DEBIAN_FRONTEND=noninteractive
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
+ENV SOC_VERSION=$SOC_VERSION
 
 RUN pip config set global.index-url ${PIP_INDEX_URL}
 

Dockerfile.a3.openEuler

@@ -20,8 +20,10 @@ FROM quay.io/ascend/cann:8.3.rc1-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"
+ARG SOC_VERSION
 
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
+ENV SOC_VERSION=$SOC_VERSION
 
 RUN pip config set global.index-url ${PIP_INDEX_URL}
 

Dockerfile.openEuler

@@ -20,8 +20,10 @@ FROM quay.io/ascend/cann:8.3.rc1-910b-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"
+ARG SOC_VERSION
 
 ENV COMPILE_CUSTOM_KERNELS=${COMPILE_CUSTOM_KERNELS}
+ENV SOC_VERSION=$SOC_VERSION
 
 RUN pip config set global.index-url ${PIP_INDEX_URL}
 

setup.py

@@ -73,7 +73,7 @@ def get_value_from_lines(lines: List[str], key: str) -> str:
     return ""
 
 
-def get_chip_info() -> str:
+def get_chip_type() -> str:
     try:
         npu_info_lines = subprocess.check_output(
             ['npu-smi', 'info', '-l']).decode().strip().split('\n')
@@ -106,19 +106,27 @@ def get_chip_info() -> str:
     except subprocess.CalledProcessError as e:
         raise RuntimeError(f"Get chip info failed: {e}")
     except FileNotFoundError:
-        # cpu envir, release code case, return `ascend910b1` by default
+        logging.warning(
-        return "ascend910b1"
+            "npu-smi command not found, if this is an npu envir, please check if npu driver is installed correctly."
+        )
+        return ""
 
 
 envs = load_module_from_path("envs",
                              os.path.join(ROOT_DIR, "vllm_ascend", "envs.py"))
 
-soc_version = get_chip_info()
+soc_version = get_chip_type()
 
 if not envs.SOC_VERSION:
+    if not soc_version:
+        raise RuntimeError(
+            "Could not determine chip type automatically via 'npu-smi'. "
+            "This can happen in a CPU-only environment. "
+            "Please set the 'SOC_VERSION' environment variable to specify the target chip."
+        )
     envs.SOC_VERSION = soc_version
 else:
-    if envs.SOC_VERSION != soc_version:
+    if soc_version and envs.SOC_VERSION != soc_version:
         logging.warning(
             f"env SOC_VERSION: {envs.SOC_VERSION} is not equal to soc_version from npu-smi: {soc_version}"
         )
@@ -126,10 +134,6 @@ else:
 
 def gen_build_info():
     soc_version = envs.SOC_VERSION
-    if "310" in soc_version and not envs.COMPILE_CUSTOM_KERNELS:
-        raise ValueError(
-            "SOC version 310 only supports custom kernels. Please set COMPILE_CUSTOM_KERNELS=1 to enable custom kernels."
-        )
 
     # TODO(zzzzwwjj): Add A5 case
     soc_to_device = {
@@ -158,6 +162,11 @@ def gen_build_info():
     assert soc_version in soc_to_device, f"Undefined soc_version: {soc_version}. Please file an issue to vllm-ascend."
     device_type = soc_to_device[soc_version]
 
+    if device_type == "_310P" and not envs.COMPILE_CUSTOM_KERNELS:
+        raise ValueError(
+            "device type 310P only supports custom kernels. Please set COMPILE_CUSTOM_KERNELS=1 to enable custom kernels."
+        )
+
     package_dir = os.path.join(ROOT_DIR, "vllm_ascend", "_build_info.py")
     with open(package_dir, "w+") as f:
         f.write('# Auto-generated file\n')