[Mini-vLLM] Cut dead subsystems: models, entrypoints, backends, utils, tests

- Drop dead model modules, keeping files live imports require
- Remove anthropic, cohere, codegen entrypoints and batch STT modes
- Delete unused attention backends, MoE experts, and NPU/XPU util leaves
- Strip dead third_party trees and ROCm leaves with no CUDA path
- Remove mooncake EC connectors: dependency missing since branch base
- Re-audit verified by full import sweep and Qwen3.5 smoke test

Co-authored-by: Hinata <hinata@idihore.id>
Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
2026-10-19 00:20:48 +07:00
co-authored by Hinata
parent 6a95f62e2f
commit 81074e94a3
940 changed files with 11 additions and 380533 deletions
-27
View File
@@ -1,27 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import warnings
from vllm.entrypoints.launchers.grpc_server import main, serve_grpc
warnings.warn(
"`vllm.entrypoints.grpc_server is deprecated and will likely be "
"unsupported in a future version. Use the corresponding function from "
"`vllm.entrypoints.launchers.grpc_server` instead.",
DeprecationWarning,
stacklevel=1,
)
__all__ = ["main", "serve_grpc"]
if __name__ == "__main__":
warnings.warn(
"`python -m vllm.entrypoints.grpc_server is deprecated and "
"will likely be unsupported in a future version. "
"Please use `vllm serve <model_path> --grpc` instead.",
DeprecationWarning,
stacklevel=1,
)
main()
+4 -185
View File
@@ -9,7 +9,7 @@ import tempfile
from argparse import Namespace
from collections.abc import Awaitable, Callable
from http import HTTPStatus
from io import BytesIO, StringIO
from io import StringIO
from typing import Any, NoReturn, TypeAlias
from urllib.parse import urlparse
@@ -17,9 +17,8 @@ import aiohttp
import pybase64 as base64
import pydantic
import torch
from fastapi import UploadFile
from prometheus_client import start_http_server
from pydantic import Field, TypeAdapter, field_validator, model_validator
from pydantic import TypeAdapter, field_validator
from pydantic_core.core_schema import ValidationInfo
from starlette.datastructures import State
from starlette.responses import JSONResponse
@@ -37,19 +36,9 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
)
from vllm.entrypoints.serve import create_error_response
from vllm.entrypoints.serve.engine.protocol import (
ErrorInfo,
ErrorResponse,
OpenAIBaseModel,
)
from vllm.entrypoints.speech_to_text.transcription.protocol import (
TranscriptionRequest,
TranscriptionResponseVariant,
)
from vllm.entrypoints.speech_to_text.translation.protocol import (
TranslationRequest,
TranslationResponse,
TranslationResponseVerbose,
)
from vllm.exceptions import VLLMValidationError
from vllm.logger import configure_logging_from_args, init_logger
from vllm.reasoning import ReasoningParserManager
@@ -76,69 +65,7 @@ def _raise_audio_filesize_limit(size_bytes: int) -> NoReturn:
)
class BatchTranscriptionRequest(TranscriptionRequest):
"""Batch transcription request that uses file_url instead of file.
This class extends TranscriptionRequest but replaces the file field
with file_url to support batch processing from audio files written in JSON format.
"""
file_url: str = Field(
...,
description=(
"Either a URL of the audio or a data URL with base64 encoded audio data. "
),
)
# Override file to be optional and unused for batch processing
file: UploadFile | None = Field(default=None, exclude=True) # type: ignore[assignment]
@model_validator(mode="before")
@classmethod
def validate_no_file(cls, data: Any):
"""Ensure file field is not provided in batch requests."""
if isinstance(data, dict) and "file" in data:
raise VLLMValidationError(
"The 'file' field is not supported in batch requests. "
"Use 'file_url' instead.",
parameter="file",
)
return data
class BatchTranslationRequest(TranslationRequest):
"""Batch translation request that uses file_url instead of file.
This class extends TranslationRequest but replaces the file field
with file_url to support batch processing from audio files written in JSON format.
"""
file_url: str = Field(
...,
description=(
"Either a URL of the audio or a data URL with base64 encoded audio data. "
),
)
# Override file to be optional and unused for batch processing
file: UploadFile | None = Field(default=None, exclude=True) # type: ignore[assignment]
@model_validator(mode="before")
@classmethod
def validate_no_file(cls, data: Any):
"""Ensure file field is not provided in batch requests."""
if isinstance(data, dict) and "file" in data:
raise VLLMValidationError(
"The 'file' field is not supported in batch requests. "
"Use 'file_url' instead.",
parameter="file",
)
return data
BatchRequestInputBody: TypeAlias = (
ChatCompletionRequest | BatchTranscriptionRequest | BatchTranslationRequest
)
BatchRequestInputBody: TypeAlias = ChatCompletionRequest
class BatchRequestInput(OpenAIBaseModel):
@@ -169,18 +96,11 @@ class BatchRequestInput(OpenAIBaseModel):
url: str = info.data["url"]
if url == "/v1/chat/completions":
return ChatCompletionRequest.model_validate(value)
if url == "/v1/audio/transcriptions":
return BatchTranscriptionRequest.model_validate(value)
if url == "/v1/audio/translations":
return BatchTranslationRequest.model_validate(value)
return TypeAdapter(BatchRequestInputBody).validate_python(value)
AllResponse: TypeAlias = (
ChatCompletionResponse
| TranscriptionResponseVariant
| TranslationResponse
| TranslationResponseVerbose
)
@@ -612,78 +532,6 @@ def handle_endpoint_request(
return run_request(handler_fn, request, tracker)
def make_transcription_wrapper(
is_translation: bool,
allowed_media_domains: list[str] | None = None,
) -> WrapperFn:
"""Factory function to create a wrapper for transcription/translation handlers.
The wrapper converts BatchTranscriptionRequest or BatchTranslationRequest
to TranscriptionRequest or TranslationRequest and calls the appropriate handler.
Args:
is_translation: If True, process as translation; otherwise process
as transcription
allowed_media_domains: If set, only URLs from these domains are
permitted for HTTP/HTTPS fetches.
Returns:
A function that takes a handler and returns a wrapped handler
"""
def wrapper(handler_fn: Callable):
async def transcription_wrapper(
batch_request_body: (BatchTranscriptionRequest | BatchTranslationRequest),
) -> (
TranscriptionResponseVariant
| TranslationResponse
| TranslationResponseVerbose
| ErrorResponse
):
try:
# Download data from URL
audio_data = await download_bytes_from_url(
batch_request_body.file_url,
allowed_media_domains=allowed_media_domains,
)
# Create a mock file from the downloaded audio data
mock_file = UploadFile(
file=BytesIO(audio_data),
filename="audio.bin",
)
# Convert batch request to regular request
# by copying all fields except file_url and setting file to mock_file
request_dict = batch_request_body.model_dump(exclude={"file_url"})
request_dict["file"] = mock_file
if is_translation:
# Create TranslationRequest from BatchTranslationRequest
translation_request = TranslationRequest.model_validate(
request_dict
)
return await handler_fn(audio_data, translation_request)
else:
# Create TranscriptionRequest from BatchTranscriptionRequest
transcription_request = TranscriptionRequest.model_validate(
request_dict
)
return await handler_fn(audio_data, transcription_request)
except Exception as e:
operation = "translation" if is_translation else "transcription"
return ErrorResponse(
error=ErrorInfo(
message=f"Failed to process {operation}: {str(e)}",
type="BadRequestError",
code=HTTPStatus.BAD_REQUEST.value,
)
)
return transcription_wrapper
return wrapper
async def build_endpoint_registry(
engine_client: EngineClient,
@@ -712,10 +560,6 @@ async def build_endpoint_registry(
# Get serving objects from state (defaulting to None if not set)
openai_serving_chat = getattr(state, "openai_serving_chat", None)
openai_serving_transcription = getattr(state, "openai_serving_transcription", None)
openai_serving_translation = getattr(state, "openai_serving_translation", None)
allowed_media_domains = getattr(args, "allowed_media_domains", None)
# Registry of endpoint configurations
endpoint_registry: dict[str, dict[str, Any]] = {
@@ -728,30 +572,6 @@ async def build_endpoint_registry(
),
"wrapper_fn": None,
},
"transcriptions": {
"url_matcher": lambda url: url == "/v1/audio/transcriptions",
"handler_getter": lambda: (
openai_serving_transcription.create_transcription
if openai_serving_transcription is not None
else None
),
"wrapper_fn": make_transcription_wrapper(
is_translation=False,
allowed_media_domains=allowed_media_domains,
),
},
"translations": {
"url_matcher": lambda url: url == "/v1/audio/translations",
"handler_getter": lambda: (
openai_serving_translation.create_translation
if openai_serving_translation is not None
else None
),
"wrapper_fn": make_transcription_wrapper(
is_translation=True,
allowed_media_domains=allowed_media_domains,
),
},
}
return endpoint_registry
@@ -812,8 +632,7 @@ async def run_batch(
make_async_error_request_output(
request,
error_msg=f"URL {request.url} was used. "
"Supported endpoints: /v1/chat/completions,"
" /v1/audio/transcriptions, /v1/audio/translations.",
"Supported endpoints: /v1/chat/completions.",
)
)
@@ -46,14 +46,6 @@ def init_entrypoints_middleware(
app.add_middleware(ScalingMiddleware)
if "realtime" in supported_tasks:
# Add WebSocket metrics middleware
from vllm.entrypoints.speech_to_text.realtime.metrics import (
WebSocketMetricsMiddleware,
)
app.add_middleware(WebSocketMetricsMiddleware)
if envs.VLLM_DEBUG_LOG_API_SERVER_RESPONSE:
logger.warning(
"CAUTION: Enabling log response in the API Server. "