[Mini-VLLM] Cut non-OpenAI surfaces, dead kernels, Mistral stack

- 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>
This commit is contained in:
2026-10-19 17:10:56 +07:00
co-authored by Hinata
parent bd70a61c20
commit 2066d3143f
1086 changed files with 122 additions and 291919 deletions
-115
View File
@@ -1,115 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import argparse
import inspect
import uvloop
from vllm.entrypoints.cli.types import CLISubcommand
from vllm.entrypoints.launchers.cli_args import (
make_arg_parser,
validate_parsed_serve_args,
)
from vllm.entrypoints.launchers.render.entry import run_launch_fastapi
from vllm.entrypoints.serve.utils.api_utils import VLLM_SUBCMD_PARSER_EPILOG
from vllm.logger import init_logger
from vllm.utils.argparse_utils import FlexibleArgumentParser
logger = init_logger(__name__)
DESCRIPTION = "Launch individual vLLM components."
class LaunchSubcommandBase(CLISubcommand):
"""The base class of subcommands for `vllm launch`."""
help: str
@classmethod
def add_cli_args(cls, parser: FlexibleArgumentParser) -> None:
"""Add the CLI arguments to the parser.
By default, uses the subcommand's docstring as the description and adds
the standard vLLM serving arguments.
Subclasses can override to add component-specific arguments.
"""
if cls.__doc__:
parser.description = inspect.cleandoc(cls.__doc__)
make_arg_parser(parser)
@staticmethod
def cmd(args: argparse.Namespace) -> None:
raise NotImplementedError
class RenderSubcommand(LaunchSubcommandBase):
"""`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`](https://docs.vllm.ai/en/latest/cli/serve/).
"""
name = "render"
help = "Launch a GPU-less rendering server (preprocessing and postprocessing only)."
@staticmethod
def cmd(args: argparse.Namespace) -> None:
uvloop.run(run_launch_fastapi(args))
class LaunchSubcommand(CLISubcommand):
"""The `launch` subcommand for the vLLM CLI.
Uses nested sub-subcommands so each component can define its own
arguments independently (e.g. ``vllm launch render``).
"""
name = "launch"
@staticmethod
def cmd(args: argparse.Namespace) -> None:
if hasattr(args, "model_tag") and args.model_tag is not None:
args.model = args.model_tag
args.launch_command(args)
def validate(self, args: argparse.Namespace) -> None:
validate_parsed_serve_args(args)
def subparser_init(
self, subparsers: argparse._SubParsersAction
) -> FlexibleArgumentParser:
launch_parser = subparsers.add_parser(
self.name,
help=DESCRIPTION,
description=DESCRIPTION,
usage=f"vllm {self.name} <component> [options]",
)
launch_subparsers = launch_parser.add_subparsers(
required=True, dest="launch_component"
)
for cmd_cls in LaunchSubcommandBase.__subclasses__():
cmd_subparser = launch_subparsers.add_parser(
cmd_cls.name,
help=cmd_cls.help,
usage=f"vllm {self.name} {cmd_cls.name} [options]",
)
cmd_subparser.set_defaults(launch_command=cmd_cls.cmd)
cmd_cls.add_cli_args(cmd_subparser)
cmd_subparser.epilog = VLLM_SUBCMD_PARSER_EPILOG.format(
subcmd=f"{self.name} {cmd_cls.name}"
)
return launch_parser
def cmd_init() -> list[CLISubcommand]:
return [LaunchSubcommand()]
-4
View File
@@ -42,10 +42,8 @@ def main():
import vllm.entrypoints.cli.collect_env
import vllm.entrypoints.cli.download_kernels
import vllm.entrypoints.cli.launch
import vllm.entrypoints.cli.openai
import vllm.entrypoints.cli.preload
import vllm.entrypoints.cli.run_batch
import vllm.entrypoints.cli.serve
from vllm.entrypoints.serve.utils.api_utils import (
VLLM_SUBCMD_PARSER_EPILOG,
@@ -56,11 +54,9 @@ def main():
CMD_MODULES = [
vllm.entrypoints.cli.openai,
vllm.entrypoints.cli.serve,
vllm.entrypoints.cli.launch,
vllm.entrypoints.cli.collect_env,
vllm.entrypoints.cli.download_kernels,
vllm.entrypoints.cli.preload,
vllm.entrypoints.cli.run_batch,
]
cli_env_setup()
-68
View File
@@ -1,68 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import argparse
import asyncio
import importlib.metadata
import typing
from vllm.entrypoints.cli.types import CLISubcommand
from vllm.entrypoints.serve.utils.api_utils import VLLM_SUBCMD_PARSER_EPILOG
from vllm.logger import init_logger
if typing.TYPE_CHECKING:
from vllm.utils.argparse_utils import FlexibleArgumentParser
else:
FlexibleArgumentParser = argparse.ArgumentParser
logger = init_logger(__name__)
class RunBatchSubcommand(CLISubcommand):
"""The `run-batch` subcommand for vLLM CLI."""
name = "run-batch"
@staticmethod
def cmd(args: argparse.Namespace) -> None:
from vllm.entrypoints.launchers.run_batch import main as run_batch_main
logger.info(
"vLLM batch processing API version %s", importlib.metadata.version("vllm")
)
logger.info("args: %s", args)
# Start the Prometheus metrics server.
# LLMEngine uses the Prometheus client
# to publish metrics at the /metrics endpoint.
if args.enable_metrics:
from prometheus_client import start_http_server
logger.info("Prometheus metrics enabled")
start_http_server(port=args.port, addr=args.url)
else:
logger.info("Prometheus metrics disabled")
asyncio.run(run_batch_main(args))
def subparser_init(
self, subparsers: argparse._SubParsersAction
) -> FlexibleArgumentParser:
from vllm.entrypoints.launchers.run_batch import make_arg_parser
run_batch_parser = subparsers.add_parser(
self.name,
help="Run batch prompts and write results to file.",
description=(
"Run batch prompts using vLLM's OpenAI-compatible API.\n"
"Supports local or HTTP input/output files."
),
usage="vllm run-batch -i INPUT.jsonl -o OUTPUT.jsonl --model <model>",
)
run_batch_parser = make_arg_parser(run_batch_parser)
run_batch_parser.epilog = VLLM_SUBCMD_PARSER_EPILOG.format(subcmd=self.name)
return run_batch_parser
def cmd_init() -> list[CLISubcommand]:
return [RunBatchSubcommand()]