[UX][Frontend] Introduce vllm preload cli for fast restart (#56680)

Signed-off-by: Isotr0py <Isotr0py@outlook.com>
This commit is contained in:
Isotr0py
2026-09-25 06:56:39 +00:00
committed by GitHub
parent 5ff3bbfb08
commit 24928a4d62
8 changed files with 496 additions and 193 deletions
@@ -177,6 +177,7 @@ BenchmarkMMProcessorSubcommand = auto_mock(
LaunchSubcommandBase = auto_mock("vllm.entrypoints.cli.launch", "LaunchSubcommandBase")
launch_description = auto_mock("vllm.entrypoints.cli.launch", "DESCRIPTION")
RenderSubcommand = auto_mock("vllm.entrypoints.cli.launch", "RenderSubcommand")
PreloadSubcommand = auto_mock("vllm.entrypoints.cli.preload", "PreloadSubcommand")
sweep_subcommands = auto_mock("vllm.benchmarks.sweep.cli", "SUBCOMMANDS")
openai_cli_args = auto_mock("vllm.entrypoints.launchers", "cli_args")
run_batch = auto_mock("vllm.entrypoints.launchers", "run_batch")
@@ -330,6 +331,7 @@ pages = {
"cli/chat.md": (create_parser(ChatCommand.add_cli_args), False),
"cli/complete.md": (create_parser(CompleteCommand.add_cli_args), False),
"cli/run-batch.md": (create_parser(run_batch.make_arg_parser), True),
"cli/preload.md": (create_parser(PreloadSubcommand.add_cli_args), True),
"cli/launch/render.md": (create_parser(RenderSubcommand.add_cli_args), True),
"cli/bench/latency.md": (create_parser(bench_latency.add_cli_args), True),
# URL kept as `mm_processor` for back-compat; command name is `mm-processor`