biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)

Browse Source 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-13 21:01:39 +08:00
committed by GitHub
parent a5bbbd2f24
commit fefce49807
128 changed files with 1221 additions and 1008 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/entrypoints/sagemaker/routes.py
View File

@@ -14,16 +14,20 @@ from vllm.entrypoints.openai.api_server import (
base,
chat,
completion,
create_chat_completion,
create_completion,
validate_json_request,
)
from vllm.entrypoints.openai.protocol import (
from vllm.entrypoints.openai.chat_completion.api_router import (
create_chat_completion,
)
from vllm.entrypoints.openai.chat_completion.protocol import (
ChatCompletionRequest,
)
from vllm.entrypoints.openai.engine.protocol import (
CompletionRequest,
ErrorResponse,
)
from vllm.entrypoints.openai.serving_engine import OpenAIServing
from vllm.entrypoints.openai.engine.serving import OpenAIServing
from vllm.entrypoints.pooling.classify.api_router import classify, create_classify
from vllm.entrypoints.pooling.classify.protocol import ClassificationRequest
from vllm.entrypoints.pooling.embed.api_router import create_embedding, embedding