Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Bugfix][Frontend] Update all fastapi requests based on OpenAPIBase with annotations #8251

Closed
wants to merge 3 commits into from
Closed

[Bugfix][Frontend] Update all fastapi requests based on OpenAPIBase with annotations #8251

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4b22aed
Update all requests based on OpenAPIBase with annotations
drikster80 Sep 6, 2024
30e3e5d
Update for mypy. Move Annotated to typing_extensions
drikster80 Sep 6, 2024
98c2e80
Merge branch 'vllm-project:main' into main
drikster80 Sep 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions vllm/entrypoints/openai/api_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import JSONResponse, Response, StreamingResponse
from starlette.routing import Mount
from typing_extensions import assert_never
from typing_extensions import assert_never, Annotated

import vllm.envs as envs
from vllm.config import ModelConfig
Expand Down Expand Up @@ -247,7 +247,7 @@ async def health() -> Response:


@router.post("/tokenize")
async def tokenize(request: TokenizeRequest):
async def tokenize(request: Annotated[dict, TokenizeRequest]):
generator = await openai_serving_tokenization.create_tokenize(request)
if isinstance(generator, ErrorResponse):
return JSONResponse(content=generator.model_dump(),
Expand All @@ -259,7 +259,7 @@ async def tokenize(request: TokenizeRequest):


@router.post("/detokenize")
async def detokenize(request: DetokenizeRequest):
async def detokenize(request: Annotated[dict, DetokenizeRequest]):
generator = await openai_serving_tokenization.create_detokenize(request)
if isinstance(generator, ErrorResponse):
return JSONResponse(content=generator.model_dump(),
Expand All @@ -283,7 +283,7 @@ async def show_version():


@router.post("/v1/chat/completions")
async def create_chat_completion(request: ChatCompletionRequest,
async def create_chat_completion(request: Annotated[dict, ChatCompletionRequest],
raw_request: Request):

generator = await openai_serving_chat.create_chat_completion(
Expand All @@ -300,7 +300,7 @@ async def create_chat_completion(request: ChatCompletionRequest,


@router.post("/v1/completions")
async def create_completion(request: CompletionRequest, raw_request: Request):
async def create_completion(request: Annotated[dict, CompletionRequest], raw_request: Request):
generator = await openai_serving_completion.create_completion(
request, raw_request)
if isinstance(generator, ErrorResponse):
Expand All @@ -313,7 +313,7 @@ async def create_completion(request: CompletionRequest, raw_request: Request):


@router.post("/v1/embeddings")
async def create_embedding(request: EmbeddingRequest, raw_request: Request):
async def create_embedding(request: Annotated[dict, EmbeddingRequest], raw_request: Request):
generator = await openai_serving_embedding.create_embedding(
request, raw_request)
if isinstance(generator, ErrorResponse):
Expand Down Expand Up @@ -351,7 +351,7 @@ async def stop_profile():
"This should ONLY be used for local development!")

@router.post("/v1/load_lora_adapter")
async def load_lora_adapter(request: LoadLoraAdapterRequest):
async def load_lora_adapter(request: Annotated[dict, LoadLoraAdapterRequest]):
response = await openai_serving_chat.load_lora_adapter(request)
if isinstance(response, ErrorResponse):
return JSONResponse(content=response.model_dump(),
Expand All @@ -365,7 +365,7 @@ async def load_lora_adapter(request: LoadLoraAdapterRequest):
return Response(status_code=200, content=response)

@router.post("/v1/unload_lora_adapter")
async def unload_lora_adapter(request: UnloadLoraAdapterRequest):
async def unload_lora_adapter(request: Annotated[dict, UnloadLoraAdapterRequest]):
response = await openai_serving_chat.unload_lora_adapter(request)
if isinstance(response, ErrorResponse):
return JSONResponse(content=response.model_dump(),
Expand Down
Loading