[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:
@@ -7,8 +7,8 @@ from collections.abc import Generator
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.openai.protocol import (
|
||||
ChatCompletionRequest,
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
DeltaMessage,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
|
||||
@@ -5,7 +5,7 @@ from unittest.mock import MagicMock
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.openai.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.tool_parsers.functiongemma_tool_parser import FunctionGemmaToolParser
|
||||
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ import json
|
||||
|
||||
import pytest
|
||||
|
||||
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.glm4_moe_tool_parser import (
|
||||
Glm4MoeModelToolParser,
|
||||
|
||||
@@ -8,7 +8,7 @@ import partial_json_parser
|
||||
import pytest
|
||||
from partial_json_parser.core.options import Allow
|
||||
|
||||
from vllm.entrypoints.openai.protocol import DeltaMessage, FunctionCall, ToolCall
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage, FunctionCall, ToolCall
|
||||
from vllm.tokenizers import TokenizerLike, get_tokenizer
|
||||
from vllm.tokenizers.detokenizer_utils import detokenize_incrementally
|
||||
from vllm.tool_parsers.jamba_tool_parser import JambaToolParser
|
||||
|
||||
@@ -6,7 +6,7 @@ import json
|
||||
|
||||
import pytest
|
||||
|
||||
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.kimi_k2_tool_parser import KimiK2ToolParser
|
||||
|
||||
|
||||
@@ -7,8 +7,10 @@ from typing import Any
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.openai.protocol import (
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionToolsParam,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
)
|
||||
|
||||
@@ -11,7 +11,7 @@ from mistral_common.protocol.instruct.request import InstructRequest
|
||||
from mistral_common.protocol.instruct.tool_calls import FunctionCall, ToolCall
|
||||
from partial_json_parser.core.options import Allow
|
||||
|
||||
from vllm.entrypoints.openai.protocol import DeltaMessage, DeltaToolCall
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage, DeltaToolCall
|
||||
from vllm.tokenizers import TokenizerLike, get_tokenizer
|
||||
from vllm.tokenizers.detokenizer_utils import detokenize_incrementally
|
||||
from vllm.tokenizers.mistral import MistralTokenizer
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
@@ -6,9 +6,11 @@ from collections.abc import Generator
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.openai.protocol import (
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionToolsParam,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
DeltaMessage,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
|
||||
@@ -7,9 +7,11 @@ from collections.abc import Generator
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.openai.protocol import (
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionToolsParam,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
DeltaMessage,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
|
||||
@@ -6,8 +6,8 @@ from collections.abc import Generator
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.openai.protocol import (
|
||||
ChatCompletionRequest,
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
DeltaMessage,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
|
||||
Reference in New Issue
Block a user