[Docs] Add comprehensive CLI reference for all large vllm subcommands (#22601)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-08-11 00:13:33 -07:00
committed by GitHub
parent 1e55dfa7e5
commit bc1d02ac85
20 changed files with 205 additions and 110 deletions
+40 -30
View File
@@ -130,28 +130,33 @@ class ChatCommand(CLISubcommand):
conversation.append(response_message) # type: ignore
print(output)
def subparser_init(
self,
subparsers: argparse._SubParsersAction) -> FlexibleArgumentParser:
chat_parser = subparsers.add_parser(
"chat",
help="Generate chat completions via the running API server.",
description="Generate chat completions via the running API server.",
usage="vllm chat [options]")
_add_query_options(chat_parser)
chat_parser.add_argument(
@staticmethod
def add_cli_args(parser: FlexibleArgumentParser) -> FlexibleArgumentParser:
"""Add CLI arguments for the chat command."""
_add_query_options(parser)
parser.add_argument(
"--system-prompt",
type=str,
default=None,
help=("The system prompt to be added to the chat template, "
"used for models that support system prompts."))
chat_parser.add_argument("-q",
"--quick",
type=str,
metavar="MESSAGE",
help=("Send a single prompt as MESSAGE "
"and print the response, then exit."))
return chat_parser
parser.add_argument("-q",
"--quick",
type=str,
metavar="MESSAGE",
help=("Send a single prompt as MESSAGE "
"and print the response, then exit."))
return parser
def subparser_init(
self,
subparsers: argparse._SubParsersAction) -> FlexibleArgumentParser:
parser = subparsers.add_parser(
"chat",
help="Generate chat completions via the running API server.",
description="Generate chat completions via the running API server.",
usage="vllm chat [options]")
return ChatCommand.add_cli_args(parser)
class CompleteCommand(CLISubcommand):
@@ -179,25 +184,30 @@ class CompleteCommand(CLISubcommand):
output = completion.choices[0].text
print(output)
def subparser_init(
self,
subparsers: argparse._SubParsersAction) -> FlexibleArgumentParser:
complete_parser = subparsers.add_parser(
"complete",
help=("Generate text completions based on the given prompt "
"via the running API server."),
description=("Generate text completions based on the given prompt "
"via the running API server."),
usage="vllm complete [options]")
_add_query_options(complete_parser)
complete_parser.add_argument(
@staticmethod
def add_cli_args(parser: FlexibleArgumentParser) -> FlexibleArgumentParser:
"""Add CLI arguments for the complete command."""
_add_query_options(parser)
parser.add_argument(
"-q",
"--quick",
type=str,
metavar="PROMPT",
help=
"Send a single prompt and print the completion output, then exit.")
return complete_parser
return parser
def subparser_init(
self,
subparsers: argparse._SubParsersAction) -> FlexibleArgumentParser:
parser = subparsers.add_parser(
"complete",
help=("Generate text completions based on the given prompt "
"via the running API server."),
description=("Generate text completions based on the given prompt "
"via the running API server."),
usage="vllm complete [options]")
return CompleteCommand.add_cli_args(parser)
def cmd_init() -> list[CLISubcommand]:
+3 -2
View File
@@ -20,7 +20,6 @@ from vllm.engine.arg_utils import AsyncEngineArgs, optional_type
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.logger import RequestLogger
# yapf: disable
from vllm.entrypoints.openai.api_server import build_async_engine_client
from vllm.entrypoints.openai.protocol import (BatchRequestInput,
BatchRequestOutput,
BatchResponseData,
@@ -34,7 +33,6 @@ from vllm.entrypoints.openai.serving_models import (BaseModelPath,
OpenAIServingModels)
from vllm.entrypoints.openai.serving_score import ServingScores
from vllm.logger import init_logger
from vllm.usage.usage_lib import UsageContext
from vllm.utils import FlexibleArgumentParser, random_uuid
from vllm.version import __version__ as VLLM_VERSION
@@ -469,6 +467,9 @@ async def run_batch(
async def main(args: Namespace):
from vllm.entrypoints.openai.api_server import build_async_engine_client
from vllm.usage.usage_lib import UsageContext
async with build_async_engine_client(
args,
usage_context=UsageContext.OPENAI_BATCH_RUNNER,