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

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

View File

@@ -14,7 +14,7 @@ from openai_harmony import (
load_harmony_encoding,
)
from vllm.entrypoints.openai.protocol import FunctionCall, ToolCall
from vllm.entrypoints.openai.engine.protocol import FunctionCall, ToolCall
from vllm.tokenizers import get_tokenizer
from vllm.tool_parsers.openai_tool_parser import OpenAIToolParser