[Frontend] Move engine/protocol.py out openai folder (#54492)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io> Signed-off-by: wang.yuqi <noooop@126.com> Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
@@ -32,6 +32,11 @@ from vllm.entrypoints.anthropic.serving import (
|
||||
AnthropicServingMessages,
|
||||
_build_anthropic_usage,
|
||||
)
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaFunctionCall,
|
||||
DeltaMessage,
|
||||
DeltaToolCall,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionResponse,
|
||||
ChatCompletionResponseChoice,
|
||||
@@ -39,13 +44,7 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionStreamResponse,
|
||||
ChatMessage,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
DeltaFunctionCall,
|
||||
DeltaMessage,
|
||||
DeltaToolCall,
|
||||
PromptTokenUsageInfo,
|
||||
UsageInfo,
|
||||
)
|
||||
from vllm.entrypoints.serve.engine.protocol import PromptTokenUsageInfo, UsageInfo
|
||||
from vllm.entrypoints.serve.exception_handling.handlers.validation import (
|
||||
validation_exception_handler,
|
||||
)
|
||||
|
||||
@@ -33,8 +33,8 @@ from vllm.entrypoints.cohere.protocol import (
|
||||
CohereChatV2Response,
|
||||
)
|
||||
from vllm.entrypoints.cohere.serving import CohereServingChatV2
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorInfo, ErrorResponse
|
||||
from vllm.entrypoints.scale_out.token_in_token_out.protocol import GenerateRequest
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorInfo, ErrorResponse
|
||||
from vllm.entrypoints.serve.exception_handling.handlers.http import (
|
||||
http_exception_handler,
|
||||
)
|
||||
|
||||
@@ -24,9 +24,9 @@ from vllm.entrypoints.generate.generative_scoring.serving import (
|
||||
GenerativeScoringResponse,
|
||||
ServingGenerativeScoring,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.openai.models.protocol import BaseModelPath
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
|
||||
from vllm.logprobs import Logprob
|
||||
from vllm.outputs import CompletionOutput, RequestOutput
|
||||
from vllm.tokenizers import get_tokenizer
|
||||
|
||||
@@ -21,7 +21,7 @@ from vllm.entrypoints.launchers.run_batch import (
|
||||
make_transcription_wrapper,
|
||||
upload_data,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.utils.mem_constants import MiB_bytes
|
||||
|
||||
|
||||
@@ -8,13 +8,13 @@ import httpx
|
||||
import pytest
|
||||
|
||||
from tests.utils import RemoteOpenAIServer
|
||||
from vllm.entrypoints.generate.base.protocol import RequestResponseMetadata
|
||||
from vllm.entrypoints.openai.chat_completion.batch_serving import (
|
||||
OpenAIServingChatBatch,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
BatchChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import RequestResponseMetadata
|
||||
from vllm.outputs import CompletionOutput, RequestOutput
|
||||
|
||||
# any model with a chat template defined in tokenizer_config should work here
|
||||
|
||||
@@ -13,11 +13,10 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
|
||||
from vllm.entrypoints.openai.engine.protocol import GenerationError
|
||||
from vllm.entrypoints.openai.models.protocol import BaseModelPath
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.scale_out.render.serving import ServingRender
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.exceptions import GenerationError, VLLMValidationError
|
||||
from vllm.outputs import CompletionOutput, RequestOutput
|
||||
from vllm.renderers.hf import HfRenderer
|
||||
from vllm.renderers.online_renderer import OnlineRenderer
|
||||
|
||||
@@ -20,6 +20,10 @@ from tests.entrypoints.openai.utils import (
|
||||
from tests.utils import RemoteOpenAIServer
|
||||
from vllm._aiter_ops import is_aiter_found_and_supported
|
||||
from vllm.config import MultiModalConfig
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaMessage,
|
||||
RequestResponseMetadata,
|
||||
)
|
||||
from vllm.entrypoints.generate.base.serving import build_per_request_timing_metrics
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
@@ -31,17 +35,13 @@ from vllm.entrypoints.openai.chat_completion.serving import (
|
||||
_make_completion_tokens_details,
|
||||
_make_prompt_tokens_details,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
DeltaMessage,
|
||||
ErrorResponse,
|
||||
RequestResponseMetadata,
|
||||
)
|
||||
from vllm.entrypoints.openai.models.serving import (
|
||||
BaseModelPath,
|
||||
OpenAIModelRegistry,
|
||||
OpenAIServingModels,
|
||||
)
|
||||
from vllm.entrypoints.openai.parser.harmony_utils import get_encoding
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.inputs import TokensPrompt
|
||||
from vllm.multimodal.inputs import PlaceholderRange
|
||||
|
||||
@@ -8,16 +8,13 @@ from unittest.mock import AsyncMock, MagicMock
|
||||
import pytest
|
||||
|
||||
from vllm.config.multimodal import MultiModalConfig
|
||||
from vllm.entrypoints.generate.base.protocol import RequestResponseMetadata
|
||||
from vllm.entrypoints.openai.completion.protocol import CompletionRequest
|
||||
from vllm.entrypoints.openai.completion.serving import OpenAIServingCompletion
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
GenerationError,
|
||||
RequestResponseMetadata,
|
||||
)
|
||||
from vllm.entrypoints.openai.models.protocol import BaseModelPath
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.scale_out.render.serving import ServingRender
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
from vllm.exceptions import GenerationError, VLLMValidationError
|
||||
from vllm.outputs import CompletionOutput, RequestOutput
|
||||
from vllm.renderers.hf import HfRenderer
|
||||
from vllm.renderers.online_renderer import OnlineRenderer
|
||||
|
||||
@@ -11,9 +11,9 @@ import pytest
|
||||
from vllm.config.multimodal import MultiModalConfig
|
||||
from vllm.entrypoints.openai.completion.protocol import CompletionRequest
|
||||
from vllm.entrypoints.openai.completion.serving import OpenAIServingCompletion
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.openai.models.protocol import BaseModelPath
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.lora.resolver import LoRAResolver, LoRAResolverRegistry
|
||||
from vllm.renderers.hf import HfRenderer
|
||||
|
||||
@@ -7,8 +7,9 @@ from unittest.mock import MagicMock
|
||||
import pytest
|
||||
|
||||
import vllm.envs as envs
|
||||
from vllm.entrypoints.generate.base.serving import GenerateBaseServing, GenerationError
|
||||
from vllm.entrypoints.generate.base.serving import GenerateBaseServing
|
||||
from vllm.envs import disable_envs_cache
|
||||
from vllm.exceptions import GenerationError
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
|
||||
@@ -11,7 +11,7 @@ from unittest.mock import MagicMock
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaMessage,
|
||||
ExtractedToolCallInformation,
|
||||
FunctionCall,
|
||||
|
||||
@@ -25,14 +25,13 @@ from openai.types.responses.tool import (
|
||||
)
|
||||
|
||||
import vllm.envs as envs
|
||||
from vllm.entrypoints.mcp.tool_server import ToolServer
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaFunctionCall,
|
||||
DeltaMessage,
|
||||
DeltaToolCall,
|
||||
ErrorResponse,
|
||||
RequestResponseMetadata,
|
||||
)
|
||||
from vllm.entrypoints.mcp.tool_server import ToolServer
|
||||
from vllm.entrypoints.openai.responses.context import ConversationContext, SimpleContext
|
||||
from vllm.entrypoints.openai.responses.protocol import (
|
||||
ResponseCreatedEvent,
|
||||
@@ -49,6 +48,7 @@ from vllm.entrypoints.openai.responses.serving import (
|
||||
from vllm.entrypoints.openai.responses.streaming_events import (
|
||||
StreamingState,
|
||||
)
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
|
||||
from vllm.inputs import tokens_input
|
||||
from vllm.outputs import CompletionOutput, RequestOutput
|
||||
from vllm.parser.harmony import Segment
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaFunctionCall,
|
||||
DeltaMessage,
|
||||
DeltaToolCall,
|
||||
|
||||
@@ -26,9 +26,9 @@ from openai.types.shared import Reasoning
|
||||
|
||||
from vllm.config.multimodal import MultiModalConfig
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
|
||||
from vllm.entrypoints.openai.responses.serving import OpenAIServingResponses
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
|
||||
from vllm.inputs import tokens_input
|
||||
from vllm.renderers.online_renderer import OnlineRenderer
|
||||
from vllm.renderers.params import ChatParams
|
||||
|
||||
@@ -5,6 +5,13 @@ import pytest
|
||||
from openai.types.chat.chat_completion import ChatCompletion as OpenAIChatCompletion
|
||||
from openai.types.chat.chat_completion_chunk import ChatCompletionChunk
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaFunctionCall,
|
||||
DeltaMessage,
|
||||
DeltaToolCall,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionResponse,
|
||||
@@ -13,15 +20,8 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionStreamResponse,
|
||||
ChatMessage,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
DeltaFunctionCall,
|
||||
DeltaMessage,
|
||||
DeltaToolCall,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
UsageInfo,
|
||||
)
|
||||
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
|
||||
from vllm.entrypoints.serve.engine.protocol import UsageInfo
|
||||
from vllm.parser.abstract_parser import DelegatingParser
|
||||
|
||||
pytestmark = pytest.mark.skip_global_cleanup
|
||||
|
||||
@@ -10,7 +10,7 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionStreamResponse,
|
||||
ChatMessage,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import UsageInfo
|
||||
from vllm.entrypoints.serve.engine.protocol import UsageInfo
|
||||
|
||||
|
||||
async def accumulate_streaming_response(
|
||||
|
||||
@@ -23,6 +23,7 @@ from vllm.entrypoints.scale_out.token_in_token_out.protocol import (
|
||||
GenerateResponseStreamChoice,
|
||||
GenerateStreamResponse,
|
||||
)
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse, UsageInfo
|
||||
|
||||
MODEL_NAME = "hmellor/tiny-random-LlamaForCausalLM"
|
||||
|
||||
@@ -40,7 +41,6 @@ def _make_stream_chunk(
|
||||
usage: dict | None = None,
|
||||
) -> GenerateStreamResponse:
|
||||
"""Build a GenerateStreamResponse SSE chunk."""
|
||||
from vllm.entrypoints.openai.engine.protocol import UsageInfo
|
||||
|
||||
return GenerateStreamResponse(
|
||||
request_id=request_id,
|
||||
@@ -61,7 +61,6 @@ def _make_usage_chunk(
|
||||
request_id: str = "test-req",
|
||||
) -> GenerateStreamResponse:
|
||||
"""Build a usage only final SSE chunk (empty choices)."""
|
||||
from vllm.entrypoints.openai.engine.protocol import UsageInfo
|
||||
|
||||
return GenerateStreamResponse(
|
||||
request_id=request_id,
|
||||
@@ -473,7 +472,6 @@ class TestServingDerenderStreamErrorHandling:
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize("exc", [KeyError("bad byte"), IndexError("oob")])
|
||||
async def test_completion_stream_bad_state_returns_400(self, exc):
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.scale_out.token_in_token_out.protocol import (
|
||||
DerenderCompletionStreamRequest,
|
||||
)
|
||||
@@ -492,7 +490,6 @@ class TestServingDerenderStreamErrorHandling:
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize("exc", [KeyError("bad byte"), IndexError("oob")])
|
||||
async def test_chat_stream_bad_state_returns_400(self, exc):
|
||||
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.scale_out.token_in_token_out.protocol import (
|
||||
DerenderChatStreamRequest,
|
||||
)
|
||||
|
||||
@@ -9,7 +9,7 @@ from unittest.mock import AsyncMock, MagicMock
|
||||
import pytest
|
||||
|
||||
from vllm.config.multimodal import MultiModalConfig
|
||||
from vllm.entrypoints.openai.engine.protocol import GenerationError, StreamOptions
|
||||
from vllm.entrypoints.generate.base.protocol import StreamOptions
|
||||
from vllm.entrypoints.openai.models.protocol import BaseModelPath
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.scale_out.token_in_token_out.protocol import (
|
||||
@@ -17,6 +17,7 @@ from vllm.entrypoints.scale_out.token_in_token_out.protocol import (
|
||||
GenerateResponse,
|
||||
)
|
||||
from vllm.entrypoints.scale_out.token_in_token_out.serving import ServingTokens
|
||||
from vllm.exceptions import GenerationError
|
||||
from vllm.logprobs import Logprob
|
||||
from vllm.outputs import CompletionOutput, RequestOutput
|
||||
from vllm.renderers import renderer_from_config
|
||||
|
||||
@@ -9,13 +9,11 @@ import pytest
|
||||
from vllm import PoolingParams
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
ErrorResponse,
|
||||
)
|
||||
from vllm.entrypoints.openai.models.protocol import BaseModelPath
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.pooling.base.serving import PoolingBaseServing
|
||||
from vllm.entrypoints.pooling.typing import PoolingServeContext
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.serve.lora.protocol import (
|
||||
LoadLoRAAdapterRequest,
|
||||
UnloadLoRAAdapterRequest,
|
||||
|
||||
@@ -5,7 +5,7 @@ from argparse import Namespace
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.openai.engine.protocol import StreamOptions
|
||||
from vllm.entrypoints.generate.base.protocol import StreamOptions
|
||||
from vllm.entrypoints.serve.utils import api_utils
|
||||
from vllm.entrypoints.serve.utils.api_utils import (
|
||||
get_max_tokens,
|
||||
|
||||
+2
-4
@@ -19,11 +19,9 @@ import pytest
|
||||
|
||||
from vllm.config import ModelConfig
|
||||
from vllm.config.speech_to_text import SpeechToTextConfig
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
ErrorResponse,
|
||||
RequestResponseMetadata,
|
||||
)
|
||||
from vllm.entrypoints.generate.base.protocol import RequestResponseMetadata
|
||||
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
|
||||
from vllm.entrypoints.serve.engine.protocol import ErrorResponse
|
||||
from vllm.entrypoints.speech_to_text.base.serving import (
|
||||
SpeechToTextBaseServing,
|
||||
asr_inter_chunk_separator,
|
||||
|
||||
@@ -13,10 +13,10 @@ import json
|
||||
from collections.abc import Sequence
|
||||
from dataclasses import dataclass, field
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
|
||||
|
||||
@dataclass
|
||||
|
||||
@@ -6,7 +6,7 @@ from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
|
||||
|
||||
def _build_token_id_map(parser) -> dict[str, int]:
|
||||
|
||||
@@ -14,10 +14,10 @@ from tests.parser.engine.streaming_helpers import (
|
||||
collect_tool_arguments,
|
||||
simulate_tool_streaming,
|
||||
)
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.parser.gemma4 import Gemma4Parser
|
||||
|
||||
# ── Special token IDs (arbitrary but consistent) ─────────────────────
|
||||
|
||||
@@ -15,15 +15,15 @@ import pytest
|
||||
import regex as re
|
||||
|
||||
from tests.parser.engine.conftest import make_mock_tokenizer
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionToolsParam,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaFunctionCall,
|
||||
DeltaToolCall,
|
||||
FunctionDefinition,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionToolsParam,
|
||||
)
|
||||
from vllm.parser.abstract_parser import DelegatingParser
|
||||
from vllm.parser.engine.adapters import make_adapters
|
||||
from vllm.parser.engine.events import EventType, SemanticEvent
|
||||
|
||||
@@ -25,16 +25,16 @@ from mistral_common.protocol.instruct.tool_calls import (
|
||||
)
|
||||
from partial_json_parser.core.options import Allow
|
||||
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaFunctionCall,
|
||||
DeltaMessage,
|
||||
DeltaToolCall,
|
||||
ExtractedToolCallInformation,
|
||||
StructuralTagResponseFormat,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.parser.engine.events import EventType
|
||||
from vllm.parser.engine.streaming_parser_engine import StreamingParserEngine
|
||||
from vllm.parser.mistral import _DEFAULT_JSON_SCHEMA, MistralParser, mistral_config
|
||||
|
||||
@@ -15,8 +15,8 @@ from openai_harmony import (
|
||||
from transformers import AutoTokenizer, GenerationConfig
|
||||
|
||||
from vllm.config import StructuredOutputsConfig, VllmConfig
|
||||
from vllm.entrypoints.generate.base.protocol import FunctionCall
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import FunctionCall
|
||||
from vllm.entrypoints.openai.parser.harmony_utils import (
|
||||
get_encoding,
|
||||
)
|
||||
|
||||
@@ -10,8 +10,8 @@ import json
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
|
||||
from vllm.parser.abstract_parser import DelegatingParser
|
||||
from vllm.reasoning.basic_parsers import BaseThinkingReasoningParser
|
||||
|
||||
@@ -6,8 +6,8 @@ from types import SimpleNamespace
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.parser.abstract_parser import DelegatingParser
|
||||
from vllm.parser.engine.registered_adapters import Qwen3ParserReasoningAdapter
|
||||
from vllm.reasoning.basic_parsers import BaseThinkingReasoningParser
|
||||
|
||||
+1
-1
@@ -4,7 +4,7 @@
|
||||
from collections.abc import Sequence
|
||||
|
||||
from vllm.config import PoolerConfig, VllmConfig
|
||||
from vllm.entrypoints.openai.engine.protocol import UsageInfo
|
||||
from vllm.entrypoints.serve.engine.protocol import UsageInfo
|
||||
from vllm.inputs import PromptType
|
||||
from vllm.outputs import PoolingRequestOutput
|
||||
from vllm.plugins.io_processors.interface import IOProcessor
|
||||
|
||||
@@ -5,11 +5,11 @@ from typing import Literal, get_args
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from vllm.entrypoints.openai.engine.protocol import UsageInfo
|
||||
from vllm.entrypoints.pooling.base.protocol import (
|
||||
CompletionRequestMixin,
|
||||
EmbedRequestMixin,
|
||||
)
|
||||
from vllm.entrypoints.serve.engine.protocol import UsageInfo
|
||||
|
||||
EmbedTask = Literal[
|
||||
"sparse",
|
||||
|
||||
+1
-1
@@ -4,7 +4,7 @@ from collections.abc import Iterator, Sequence
|
||||
from typing import cast
|
||||
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.entrypoints.openai.engine.protocol import UsageInfo
|
||||
from vllm.entrypoints.serve.engine.protocol import UsageInfo
|
||||
from vllm.inputs import PromptType, TokensPrompt
|
||||
from vllm.outputs import PoolingRequestOutput
|
||||
from vllm.plugins.io_processors.interface import IOProcessor
|
||||
|
||||
@@ -5,8 +5,8 @@ from typing import Literal, get_args
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from vllm.entrypoints.openai.engine.protocol import UsageInfo
|
||||
from vllm.entrypoints.pooling.base.protocol import CompletionRequestMixin
|
||||
from vllm.entrypoints.serve.engine.protocol import UsageInfo
|
||||
|
||||
InputType = Literal["query", "document"]
|
||||
INPUT_TYPES: tuple[InputType, ...] = get_args(InputType)
|
||||
|
||||
@@ -12,14 +12,14 @@ from typing import Any
|
||||
import pytest
|
||||
from pydantic import ValidationError
|
||||
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
JsonSchemaResponseFormat,
|
||||
ResponseFormat,
|
||||
StructuralTagResponseFormat,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
|
||||
from vllm.reasoning.cohere_command_reasoning_parser import (
|
||||
CohereCommand3ReasoningParser,
|
||||
|
||||
@@ -4,8 +4,8 @@
|
||||
import pytest
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.reasoning import ReasoningParserManager
|
||||
from vllm.reasoning.deepseek_r1_reasoning_parser import DeepSeekR1ReasoningParser
|
||||
from vllm.reasoning.deepseek_v3_reasoning_parser import DeepSeekV3ReasoningParser
|
||||
|
||||
@@ -5,8 +5,8 @@ from unittest.mock import MagicMock
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.reasoning.kimi_k2_reasoning_parser import KimiK2ReasoningParser
|
||||
from vllm.tokenizers import get_tokenizer
|
||||
|
||||
|
||||
@@ -3,10 +3,10 @@
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.parser.kimi_k3 import KimiK3Parser
|
||||
from vllm.parser.parser_manager import ParserManager
|
||||
from vllm.reasoning.kimi_k3_reasoning_parser import KimiK3ReasoningParser
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.reasoning import ReasoningParser
|
||||
from vllm.utils.mistral import is_mistral_tokenizer
|
||||
|
||||
|
||||
@@ -7,11 +7,11 @@ from unittest.mock import MagicMock
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionToolsParam,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.tool_parsers import ToolParserManager
|
||||
from vllm.tool_parsers.dots_tool_parser import DotsToolParser
|
||||
|
||||
|
||||
@@ -7,12 +7,12 @@ from collections.abc import Generator
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaMessage,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.tokenizers import TokenizerLike, get_tokenizer
|
||||
from vllm.tokenizers.detokenizer_utils import detokenize_incrementally
|
||||
from vllm.tool_parsers.ernie45_tool_parser import Ernie45ToolParser
|
||||
|
||||
@@ -10,7 +10,7 @@ from tests.tool_parsers.utils import (
|
||||
run_tool_extraction,
|
||||
run_tool_extraction_streaming,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import FunctionCall
|
||||
from vllm.entrypoints.generate.base.protocol import FunctionCall
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.tool_parsers import ToolParser, ToolParserManager
|
||||
|
||||
|
||||
@@ -9,12 +9,12 @@ from unittest.mock import Mock
|
||||
import pytest
|
||||
from openai.types.responses import ResponseFunctionToolCall
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import FunctionCall
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionToolsParam,
|
||||
FunctionDefinition,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import FunctionCall
|
||||
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
|
||||
from vllm.entrypoints.openai.responses.utils import build_response_output_items
|
||||
from vllm.tokenizers import get_tokenizer
|
||||
|
||||
@@ -7,10 +7,10 @@ from typing import Any
|
||||
import pytest
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaMessage,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.tool_parsers.granite4_tool_parser import Granite4ToolParser
|
||||
|
||||
MODEL = "ibm-granite/granite-4.0-h-tiny"
|
||||
|
||||
@@ -11,7 +11,7 @@ from tests.tool_parsers.utils import (
|
||||
run_tool_extraction,
|
||||
run_tool_extraction_streaming,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import FunctionCall, ToolCall
|
||||
from vllm.entrypoints.generate.base.protocol import FunctionCall, ToolCall
|
||||
from vllm.tool_parsers import ToolParser, ToolParserManager
|
||||
|
||||
|
||||
|
||||
@@ -8,12 +8,12 @@ from unittest.mock import Mock
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionToolsParam,
|
||||
FunctionDefinition,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.tokenizers import get_tokenizer
|
||||
from vllm.tool_parsers.hy_v3_tool_parser import HYV3ToolParser
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@ import partial_json_parser
|
||||
import pytest
|
||||
from partial_json_parser.core.options import Allow
|
||||
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage, FunctionCall, ToolCall
|
||||
from vllm.entrypoints.generate.base.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
|
||||
|
||||
@@ -10,7 +10,7 @@ from tests.tool_parsers.utils import (
|
||||
run_tool_extraction,
|
||||
run_tool_extraction_streaming,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import FunctionCall
|
||||
from vllm.entrypoints.generate.base.protocol import FunctionCall
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.tool_parsers import ToolParser, ToolParserManager
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ from unittest.mock import MagicMock, patch
|
||||
import pytest
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
from vllm.entrypoints.openai.engine.protocol import ExtractedToolCallInformation
|
||||
from vllm.entrypoints.generate.base.protocol import ExtractedToolCallInformation
|
||||
from vllm.tool_parsers.llama_tool_parser import Llama3JsonToolParser
|
||||
|
||||
LLAMA_MODEL = "meta-llama/Llama-3.2-1B-Instruct"
|
||||
|
||||
@@ -9,7 +9,7 @@ from tests.tool_parsers.utils import (
|
||||
run_tool_extraction,
|
||||
run_tool_extraction_streaming,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import FunctionCall
|
||||
from vllm.entrypoints.generate.base.protocol import FunctionCall
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.tool_parsers import ToolParser, ToolParserManager
|
||||
|
||||
|
||||
@@ -9,11 +9,11 @@ from unittest.mock import MagicMock
|
||||
import pytest
|
||||
|
||||
from tests.tool_parsers.utils import run_tool_extraction_streaming
|
||||
from vllm.entrypoints.generate.base.protocol import FunctionCall, ToolCall
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionToolsParam,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import FunctionCall, ToolCall
|
||||
from vllm.tool_parsers import ToolParser, ToolParserManager
|
||||
from vllm.tool_parsers.minicpm5xml_tool_parser import MiniCPM5XMLToolParser
|
||||
|
||||
|
||||
@@ -6,11 +6,11 @@ from typing import Any
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionToolsParam,
|
||||
FunctionDefinition,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.tool_parsers import ToolParserManager
|
||||
from vllm.tool_parsers.minimax_m3_tool_parser import MinimaxM3ToolParser
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ from tests.tool_parsers.utils import (
|
||||
run_tool_extraction,
|
||||
run_tool_extraction_streaming,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import FunctionCall
|
||||
from vllm.entrypoints.generate.base.protocol import FunctionCall
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.tool_parsers import ToolParser, ToolParserManager
|
||||
|
||||
|
||||
@@ -9,7 +9,7 @@ from tests.tool_parsers.utils import (
|
||||
run_tool_extraction,
|
||||
run_tool_extraction_streaming,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import FunctionCall
|
||||
from vllm.entrypoints.generate.base.protocol import FunctionCall
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.tool_parsers import ToolParser, ToolParserManager
|
||||
|
||||
|
||||
@@ -9,6 +9,11 @@ import pytest
|
||||
from openai.types.responses.function_tool import FunctionTool
|
||||
from xgrammar import StructuralTag
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaMessage,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionNamedFunction,
|
||||
ChatCompletionNamedToolChoiceParam,
|
||||
@@ -16,11 +21,6 @@ from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionToolsParam,
|
||||
FunctionDefinition,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
DeltaMessage,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
)
|
||||
from vllm.parser.abstract_parser import DelegatingParser
|
||||
from vllm.tokenizers import TokenizerLike, get_tokenizer
|
||||
from vllm.tokenizers.detokenizer_utils import detokenize_incrementally
|
||||
|
||||
@@ -6,15 +6,15 @@ from collections.abc import Generator
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionToolsParam,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaMessage,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionToolsParam,
|
||||
)
|
||||
from vllm.tokenizers import TokenizerLike, get_tokenizer
|
||||
from vllm.tokenizers.detokenizer_utils import detokenize_incrementally
|
||||
from vllm.tool_parsers.step3p5_tool_parser import Step3p5ToolParser
|
||||
|
||||
@@ -6,12 +6,12 @@ from collections.abc import Generator
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaMessage,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.tokenizers import TokenizerLike, get_tokenizer
|
||||
from vllm.tokenizers.detokenizer_utils import detokenize_incrementally
|
||||
from vllm.tool_parsers.xlam_tool_parser import xLAMToolParser
|
||||
|
||||
@@ -3,13 +3,13 @@
|
||||
|
||||
from collections.abc import Iterable
|
||||
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
from vllm.entrypoints.generate.base.protocol import (
|
||||
DeltaMessage,
|
||||
ExtractedToolCallInformation,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.tokenizers import TokenizerLike
|
||||
from vllm.tool_parsers import ToolParser
|
||||
|
||||
|
||||
@@ -5,10 +5,10 @@ import json
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.generate.base.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import DeltaMessage
|
||||
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
|
||||
from vllm.entrypoints.openai.responses.utils import build_response_output_items
|
||||
from vllm.exceptions import VLLMValidationError
|
||||
|
||||
Reference in New Issue
Block a user