[Doc] Sync CLI guide with actual help modes and launch subcommand (#40326)
Signed-off-by: Rui Wang <raygorous@gmail.com> Co-authored-by: Rui Wang <raygorous@gmail.com>
This commit is contained in:
@@ -6,3 +6,5 @@ nav:
|
|||||||
- run-batch.md
|
- run-batch.md
|
||||||
- vllm bench:
|
- vllm bench:
|
||||||
- bench/**/*.md
|
- bench/**/*.md
|
||||||
|
- vllm launch:
|
||||||
|
- launch/**/*.md
|
||||||
|
|||||||
+20
-8
@@ -9,7 +9,7 @@ vllm --help
|
|||||||
Available Commands:
|
Available Commands:
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
vllm {chat,complete,serve,bench,collect-env,run-batch}
|
vllm {chat,complete,serve,launch,bench,collect-env,run-batch}
|
||||||
```
|
```
|
||||||
|
|
||||||
## serve
|
## serve
|
||||||
@@ -37,24 +37,36 @@ vllm serve meta-llama/Llama-2-7b-hf --uds /tmp/vllm.sock
|
|||||||
Check with --help for more options:
|
Check with --help for more options:
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
# To list all groups
|
# To list all flags
|
||||||
vllm serve --help=listgroup
|
vllm serve --help=all
|
||||||
|
|
||||||
# To view a argument group
|
# To view an argument group
|
||||||
vllm serve --help=ModelConfig
|
vllm serve --help=ModelConfig
|
||||||
|
|
||||||
# To view a single argument
|
# To view a single argument
|
||||||
vllm serve --help=max-num-seqs
|
vllm serve --help=max-num-seqs
|
||||||
|
|
||||||
# To search by keyword
|
# To search by keyword or flag name
|
||||||
vllm serve --help=max
|
vllm serve --help=max
|
||||||
|
|
||||||
# To view full help with pager (less/more)
|
|
||||||
vllm serve --help=page
|
|
||||||
```
|
```
|
||||||
|
|
||||||
See [vllm serve](./serve.md) for the full reference of all available arguments.
|
See [vllm serve](./serve.md) for the full reference of all available arguments.
|
||||||
|
|
||||||
|
## launch
|
||||||
|
|
||||||
|
Launch individual vLLM components.
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Launch the rendering server component
|
||||||
|
vllm launch render meta-llama/Llama-3.2-1B-Instruct
|
||||||
|
|
||||||
|
# Inspect all available flags for the render component
|
||||||
|
vllm launch render --help=all
|
||||||
|
```
|
||||||
|
|
||||||
|
See [vllm launch render](./launch/render.md) for the current launch
|
||||||
|
component reference.
|
||||||
|
|
||||||
## chat
|
## chat
|
||||||
|
|
||||||
Generate chat completions via the running API server.
|
Generate chat completions via the running API server.
|
||||||
|
|||||||
@@ -0,0 +1,22 @@
|
|||||||
|
# vllm launch render
|
||||||
|
|
||||||
|
## Overview
|
||||||
|
|
||||||
|
`vllm launch render` starts a GPU-less rendering server for preprocessing and
|
||||||
|
postprocessing only.
|
||||||
|
|
||||||
|
```bash
|
||||||
|
vllm launch render meta-llama/Llama-3.2-1B-Instruct --port 8100
|
||||||
|
```
|
||||||
|
|
||||||
|
This command reuses the standard serving parser, so model, frontend,
|
||||||
|
networking, and related CLI options follow the same conventions as
|
||||||
|
[`vllm serve`](../serve.md).
|
||||||
|
|
||||||
|
## JSON CLI Arguments
|
||||||
|
|
||||||
|
--8<-- "docs/cli/json_tip.inc.md"
|
||||||
|
|
||||||
|
## Arguments
|
||||||
|
|
||||||
|
--8<-- "docs/generated/argparse/launch_render.inc.md"
|
||||||
@@ -147,6 +147,7 @@ AsyncEngineArgs = auto_mock("vllm.engine.arg_utils", "AsyncEngineArgs")
|
|||||||
EngineArgs = auto_mock("vllm.engine.arg_utils", "EngineArgs")
|
EngineArgs = auto_mock("vllm.engine.arg_utils", "EngineArgs")
|
||||||
ChatCommand = auto_mock("vllm.entrypoints.cli.openai", "ChatCommand")
|
ChatCommand = auto_mock("vllm.entrypoints.cli.openai", "ChatCommand")
|
||||||
CompleteCommand = auto_mock("vllm.entrypoints.cli.openai", "CompleteCommand")
|
CompleteCommand = auto_mock("vllm.entrypoints.cli.openai", "CompleteCommand")
|
||||||
|
RenderSubcommand = auto_mock("vllm.entrypoints.cli.launch", "RenderSubcommand")
|
||||||
openai_cli_args = auto_mock("vllm.entrypoints.openai", "cli_args")
|
openai_cli_args = auto_mock("vllm.entrypoints.openai", "cli_args")
|
||||||
openai_run_batch = auto_mock("vllm.entrypoints.openai", "run_batch")
|
openai_run_batch = auto_mock("vllm.entrypoints.openai", "run_batch")
|
||||||
|
|
||||||
@@ -260,6 +261,7 @@ def on_startup(command: Literal["build", "gh-deploy", "serve"], dirty: bool):
|
|||||||
"serve": create_parser(openai_cli_args.make_arg_parser),
|
"serve": create_parser(openai_cli_args.make_arg_parser),
|
||||||
"chat": create_parser(ChatCommand.add_cli_args),
|
"chat": create_parser(ChatCommand.add_cli_args),
|
||||||
"complete": create_parser(CompleteCommand.add_cli_args),
|
"complete": create_parser(CompleteCommand.add_cli_args),
|
||||||
|
"launch_render": create_parser(RenderSubcommand.add_cli_args),
|
||||||
"run-batch": create_parser(openai_run_batch.make_arg_parser),
|
"run-batch": create_parser(openai_run_batch.make_arg_parser),
|
||||||
# Benchmark CLI
|
# Benchmark CLI
|
||||||
"bench_latency": create_parser(bench_latency.add_cli_args),
|
"bench_latency": create_parser(bench_latency.add_cli_args),
|
||||||
|
|||||||
Reference in New Issue
Block a user