Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
71 lines
2.3 KiB
Python
71 lines
2.3 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
|
|
from http import HTTPStatus
|
|
|
|
from fastapi import APIRouter, Depends, FastAPI, Request
|
|
from fastapi.responses import JSONResponse, StreamingResponse
|
|
|
|
from vllm.entrypoints.openai.completion.protocol import (
|
|
CompletionRequest,
|
|
CompletionResponse,
|
|
)
|
|
from vllm.entrypoints.openai.completion.serving import OpenAIServingCompletion
|
|
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
|
from vllm.entrypoints.openai.orca_metrics import metrics_header
|
|
from vllm.entrypoints.openai.utils import validate_json_request
|
|
from vllm.entrypoints.utils import (
|
|
load_aware_call,
|
|
with_cancellation,
|
|
)
|
|
from vllm.logger import init_logger
|
|
|
|
logger = init_logger(__name__)
|
|
|
|
router = APIRouter()
|
|
ENDPOINT_LOAD_METRICS_FORMAT_HEADER_LABEL = "endpoint-load-metrics-format"
|
|
|
|
|
|
def completion(request: Request) -> OpenAIServingCompletion | None:
|
|
return request.app.state.openai_serving_completion
|
|
|
|
|
|
@router.post(
|
|
"/v1/completions",
|
|
dependencies=[Depends(validate_json_request)],
|
|
responses={
|
|
HTTPStatus.OK.value: {"content": {"text/event-stream": {}}},
|
|
HTTPStatus.BAD_REQUEST.value: {"model": ErrorResponse},
|
|
HTTPStatus.NOT_FOUND.value: {"model": ErrorResponse},
|
|
HTTPStatus.INTERNAL_SERVER_ERROR.value: {"model": ErrorResponse},
|
|
},
|
|
)
|
|
@with_cancellation
|
|
@load_aware_call
|
|
async def create_completion(request: CompletionRequest, raw_request: Request):
|
|
metrics_header_format = raw_request.headers.get(
|
|
ENDPOINT_LOAD_METRICS_FORMAT_HEADER_LABEL, ""
|
|
)
|
|
handler = completion(raw_request)
|
|
if handler is None:
|
|
raise NotImplementedError("The model does not support Completions API")
|
|
|
|
generator = await handler.create_completion(request, raw_request)
|
|
|
|
if isinstance(generator, ErrorResponse):
|
|
return JSONResponse(
|
|
content=generator.model_dump(), status_code=generator.error.code
|
|
)
|
|
elif isinstance(generator, CompletionResponse):
|
|
return JSONResponse(
|
|
content=generator.model_dump(),
|
|
headers=metrics_header(metrics_header_format),
|
|
)
|
|
|
|
return StreamingResponse(content=generator, media_type="text/event-stream")
|
|
|
|
|
|
def attach_router(app: FastAPI):
|
|
app.include_router(router)
|