[Misc] add collect_env to cli and docker image (#16759)

Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>

.github/ISSUE_TEMPLATE/200-installation.yml

@@ -14,7 +14,7 @@ body:
     description: |
       Please run the following and paste the output below.
       ```sh
-      wget https://raw.githubusercontent.com/vllm-project/vllm/main/collect_env.py
+      wget https://raw.githubusercontent.com/vllm-project/vllm/main/vllm/collect_env.py
       # For security purposes, please feel free to check the contents of collect_env.py before running it.
       python collect_env.py
       ```

.github/ISSUE_TEMPLATE/300-usage.yml

@@ -14,7 +14,7 @@ body:
     description: |
       Please run the following and paste the output below.
       ```sh
-      wget https://raw.githubusercontent.com/vllm-project/vllm/main/collect_env.py
+      wget https://raw.githubusercontent.com/vllm-project/vllm/main/vllm/collect_env.py
       # For security purposes, please feel free to check the contents of collect_env.py before running it.
       python collect_env.py
       ```

.github/ISSUE_TEMPLATE/400-bug-report.yml

@@ -14,7 +14,7 @@ body:
     description: |
       Please run the following and paste the output below.
       ```sh
-      wget https://raw.githubusercontent.com/vllm-project/vllm/main/collect_env.py
+      wget https://raw.githubusercontent.com/vllm-project/vllm/main/vllm/collect_env.py
       # For security purposes, please feel free to check the contents of collect_env.py before running it.
       python collect_env.py
       ```

.github/ISSUE_TEMPLATE/700-performance-discussion.yml

@@ -35,7 +35,7 @@ body:
     description: |
       Please run the following and paste the output below.
       ```sh
-      wget https://raw.githubusercontent.com/vllm-project/vllm/main/collect_env.py
+      wget https://raw.githubusercontent.com/vllm-project/vllm/main/vllm/collect_env.py
       # For security purposes, please feel free to check the contents of collect_env.py before running it.
       python collect_env.py
       ```

docker/Dockerfile

@@ -241,6 +241,7 @@ if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
 fi
 COPY examples examples
 COPY benchmarks benchmarks
+COPY ./vllm/collect_env.py .
 
 # Although we build Flashinfer with AOT mode, there's still
 # some issues w.r.t. JIT compilation. Therefore we need to

docker/Dockerfile.cpu

@@ -121,6 +121,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
 ADD ./tests/ ./tests/
 ADD ./examples/ ./examples/
 ADD ./benchmarks/ ./benchmarks/
+ADD ./vllm/collect_env.py .
 
 # install development dependencies (for testing)
 RUN --mount=type=cache,target=/root/.cache/uv \

collect_env.py → vllm/collect_env.py

@@ -283,12 +283,13 @@ def get_vllm_version():
     if __version__ == "dev":
         return "N/A (dev)"
 
-    if len(__version_tuple__) == 4: # dev build
-        git_sha = __version_tuple__[-1][1:] # type: ignore
+    if len(__version_tuple__) == 4:  # dev build
+        git_sha = __version_tuple__[-1][1:]  # type: ignore
         return f"{__version__} (git sha: {git_sha}"
 
     return __version__
 
+
 def summarize_vllm_build_flags():
     # This could be a static method if the flags are constant, or dynamic if you need to check environment variables, etc.
     return 'CUDA Archs: {}; ROCm: {}; Neuron: {}'.format(
@@ -502,7 +503,9 @@ def get_pip_packages(run_lambda, patterns=None):
             print("uv is set")
             cmd = ["uv", "pip", "list", "--format=freeze"]
         else:
-            raise RuntimeError("Could not collect pip list output (pip or uv module not available)")
+            raise RuntimeError(
+                "Could not collect pip list output (pip or uv module not available)"
+            )
 
         out = run_and_read_all(run_lambda, cmd)
         return "\n".join(line for line in out.splitlines()
@@ -535,13 +538,12 @@ def is_xnnpack_available():
     else:
         return "N/A"
 
+
 def get_env_vars():
     env_vars = ''
-    secret_terms=('secret', 'token', 'api', 'access', 'password')
-    report_prefix = ("TORCH", "NCCL", "PYTORCH",
-                     "CUDA", "CUBLAS", "CUDNN",
-                     "OMP_", "MKL_",
-                     "NVIDIA")
+    secret_terms = ('secret', 'token', 'api', 'access', 'password')
+    report_prefix = ("TORCH", "NCCL", "PYTORCH", "CUDA", "CUBLAS", "CUDNN",
+                     "OMP_", "MKL_", "NVIDIA")
     for k, v in os.environ.items():
         if any(term in k.lower() for term in secret_terms):
             continue
@@ -552,6 +554,7 @@ def get_env_vars():
 
     return env_vars
 
+
 def get_env_info():
     run_lambda = run
     pip_version, pip_list_output = get_pip_packages(run_lambda)

vllm/entrypoints/cli/collect_env.py

+# SPDX-License-Identifier: Apache-2.0
+
+import argparse
+
+from vllm.collect_env import main as collect_env_main
+from vllm.entrypoints.cli.types import CLISubcommand
+from vllm.entrypoints.openai.cli_args import make_arg_parser
+from vllm.utils import FlexibleArgumentParser
+
+
+class CollectEnvSubcommand(CLISubcommand):
+    """The `serve` subcommand for the vLLM CLI. """
+
+    def __init__(self):
+        self.name = "collect-env"
+        super().__init__()
+
+    @staticmethod
+    def cmd(args: argparse.Namespace) -> None:
+        """Collect information about the environment."""
+        collect_env_main()
+
+    def subparser_init(
+            self,
+            subparsers: argparse._SubParsersAction) -> FlexibleArgumentParser:
+        serve_parser = subparsers.add_parser(
+            "collect-env",
+            help="Start collecting environment information.",
+            description="Start collecting environment information.",
+            usage="vllm collect-env")
+        return make_arg_parser(serve_parser)
+
+
+def cmd_init() -> list[CLISubcommand]:
+    return [CollectEnvSubcommand()]

vllm/entrypoints/cli/main.py

@@ -5,6 +5,7 @@ import signal
 import sys
 
 import vllm.entrypoints.cli.benchmark.main
+import vllm.entrypoints.cli.collect_env
 import vllm.entrypoints.cli.openai
 import vllm.entrypoints.cli.serve
 import vllm.version
@@ -15,6 +16,7 @@ CMD_MODULES = [
     vllm.entrypoints.cli.openai,
     vllm.entrypoints.cli.serve,
     vllm.entrypoints.cli.benchmark.main,
+    vllm.entrypoints.cli.collect_env,
 ]