[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:
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user