MOVZXandHinata
2066d3143f
- Remove Anthropic, Cohere, SageMaker, decisions, structured-decisions, rl, render-launcher and batch entrypoints; keep scale-out token routes - Drop the Swagger static bundle and the /docs, /redoc routes - Delete device-keyed tuning configs for fused_moe, quant utils, mamba select-state and helion; no sm86 entry ever existed for any of them - Remove ten unused rope variants plus the fbgemm_fp8 and fp_quant quantizers and their config, metrics and loader plumbing - Cut the CPU device build: csrc/cpu, cpu_extension.cmake, cpu requirements and the setup.py cpu target path - Delete 29 environment variables nothing reads and 14 chat-template fallbacks for models this fork no longer registers - Remove nine dead CUDA ops (deepseek_v4, kimi_k3, minimax, muse_spark, dsv3 gemm) with their kernels, bindings, wrappers and CMake entries - Delete the connector test suites that targeted removed connectors - Cut the Mistral tokenizer and parser stack, its tests, and the mistral_common and ijson dependency pins - Restore the Qwen4Exp registry rows and nvidia/mtp.py that an earlier cut deleted while keeping the model tree Co-authored-by: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
95 lines
2.7 KiB
Python
95 lines
2.7 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
"""The CLI entrypoints of vLLM.
|
|
|
|
Note that all future modules must be lazily loaded within main
|
|
to avoid certain eager import breakage."""
|
|
|
|
import importlib.metadata
|
|
import sys
|
|
from importlib.util import find_spec
|
|
|
|
from vllm.logger import configure_logging_from_args, init_logger
|
|
|
|
logger = init_logger(__name__)
|
|
|
|
|
|
def maybe_run_omni() -> bool:
|
|
# If `--omni` arg is passed to the CLI, delegate to vLLM Omni's entrypoint handling
|
|
if "--omni" not in sys.argv:
|
|
return False
|
|
|
|
# NOTE: Check the spec instead of importing directly here, since things could
|
|
# fail with ImportError due to mismatched versions if things are moved around.
|
|
spec = find_spec("vllm_omni")
|
|
if spec is None:
|
|
logger.error(
|
|
"--omni flag requires a valid instance of vllm-omni to be installed."
|
|
)
|
|
sys.exit(1)
|
|
|
|
from vllm_omni.entrypoints.cli.main import main as omni_main
|
|
|
|
logger.info("Delegating entrypoint handling to vllm-omni")
|
|
omni_main()
|
|
|
|
return True
|
|
|
|
|
|
def main():
|
|
if maybe_run_omni():
|
|
return
|
|
|
|
import vllm.entrypoints.cli.collect_env
|
|
import vllm.entrypoints.cli.download_kernels
|
|
import vllm.entrypoints.cli.openai
|
|
import vllm.entrypoints.cli.preload
|
|
import vllm.entrypoints.cli.serve
|
|
from vllm.entrypoints.serve.utils.api_utils import (
|
|
VLLM_SUBCMD_PARSER_EPILOG,
|
|
cli_env_setup,
|
|
)
|
|
from vllm.utils.argparse_utils import FlexibleArgumentParser
|
|
|
|
CMD_MODULES = [
|
|
vllm.entrypoints.cli.openai,
|
|
vllm.entrypoints.cli.serve,
|
|
vllm.entrypoints.cli.collect_env,
|
|
vllm.entrypoints.cli.download_kernels,
|
|
vllm.entrypoints.cli.preload,
|
|
]
|
|
|
|
cli_env_setup()
|
|
|
|
parser = FlexibleArgumentParser(
|
|
description="vLLM CLI",
|
|
epilog=VLLM_SUBCMD_PARSER_EPILOG.format(subcmd="[subcommand]"),
|
|
)
|
|
parser.add_argument(
|
|
"-v",
|
|
"--version",
|
|
action="version",
|
|
version=importlib.metadata.version("vllm"),
|
|
)
|
|
subparsers = parser.add_subparsers(required=False, dest="subparser")
|
|
cmds = {}
|
|
for cmd_module in CMD_MODULES:
|
|
new_cmds = cmd_module.cmd_init()
|
|
for cmd in new_cmds:
|
|
cmd.subparser_init(subparsers).set_defaults(dispatch_function=cmd.cmd)
|
|
cmds[cmd.name] = cmd
|
|
args = parser.parse_args()
|
|
if args.subparser in cmds:
|
|
cmd = cmds[args.subparser]
|
|
configure_logging_from_args(args)
|
|
cmd.validate(args)
|
|
|
|
if hasattr(args, "dispatch_function"):
|
|
args.dispatch_function(args)
|
|
else:
|
|
parser.print_help()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|