[Frontend][Build] Add vllm download-kernels for FlashInfer precompiled kernels (#58765)

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Misha Goin
2026-10-09 21:22:35 -07:00
committed by GitHub
co-authored by Claude Opus 5.5
parent be0823357f
commit 29e4d2d42e
15 changed files with 309 additions and 20 deletions
@@ -178,6 +178,9 @@ LaunchSubcommandBase = auto_mock("vllm.entrypoints.cli.launch", "LaunchSubcomman
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")
DownloadKernelsSubcommand = auto_mock(
"vllm.entrypoints.cli.download_kernels", "DownloadKernelsSubcommand"
)
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")
@@ -332,6 +335,10 @@ pages = {
"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/download-kernels.md": (
create_parser(DownloadKernelsSubcommand.add_cli_args),
False,
),
"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`