[Misc] mv chat_utils.py to renderers. (#60522)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-10-10 06:50:34 +00:00
committed by GitHub
parent 699c892dd5
commit c1692c85f1
101 changed files with 185 additions and 187 deletions
@@ -8,7 +8,7 @@ import regex as re
from tests.entrypoints.multimodal.conftest import TEST_IMAGE_ASSETS
from vllm import LLM
from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
from vllm.renderers.chat_utils import ChatCompletionMessageParam
from vllm.v1.metrics import loggers as stat_loggers
from vllm.v1.metrics.reader import Counter, Metric
@@ -7,9 +7,9 @@ from unittest.mock import Mock
import pytest
from vllm import LLM, SamplingParams
from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
from vllm.inputs import TextPrompt
from vllm.outputs import RequestOutput
from vllm.renderers.chat_utils import ChatCompletionMessageParam
def _make_mock_llm() -> LLM:
@@ -18,7 +18,6 @@ from tests.models.language.pooling.embed_utils import (
)
from tests.models.utils import check_embeddings_close
from tests.utils import RemoteOpenAIServer
from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
from vllm.entrypoints.pooling.embed.protocol import EmbeddingResponse
from vllm.entrypoints.pooling.pooling.protocol import PoolingResponse
from vllm.entrypoints.pooling.utils import (
@@ -27,6 +26,7 @@ from vllm.entrypoints.pooling.utils import (
decode_pooling_output,
)
from vllm.platforms import current_platform
from vllm.renderers.chat_utils import ChatCompletionMessageParam
from vllm.tokenizers import get_tokenizer
from vllm.utils.serial_utils import EMBED_DTYPES, ENDIANNESS, binary2tensor
@@ -11,13 +11,13 @@ import torch
from tests.models.utils import check_embeddings_close
from tests.utils import RemoteOpenAIServer
from vllm.entrypoints.chat_utils import ChatCompletionMessageParam
from vllm.entrypoints.pooling.pooling.protocol import PoolingResponse
from vllm.entrypoints.pooling.utils import (
MetadataItem,
build_metadata_items,
decode_pooling_output,
)
from vllm.renderers.chat_utils import ChatCompletionMessageParam
from vllm.tokenizers import get_tokenizer
from vllm.utils.serial_utils import EMBED_DTYPES, ENDIANNESS, binary2tensor
+3 -3
View File
@@ -11,12 +11,12 @@ from safetensors.torch import load_file
from transformers import AutoModel, AutoTokenizer
from tests.conftest import HfRunner
from vllm.entrypoints.chat_utils import (
from vllm.entrypoints.pooling.scoring.typing import ScoreMultiModalParam
from vllm.entrypoints.pooling.scoring.utils import compute_maxsim_score
from vllm.renderers.chat_utils import (
ChatCompletionContentPartImageParam,
ChatCompletionContentPartTextParam,
)
from vllm.entrypoints.pooling.scoring.typing import ScoreMultiModalParam
from vllm.entrypoints.pooling.scoring.utils import compute_maxsim_score
from vllm.transformers_utils.repo_utils import hf_api
@@ -6,7 +6,7 @@ from unittest.mock import MagicMock
import pytest
from vllm.entrypoints.chat_utils import _parse_chat_message_content
from vllm.renderers.chat_utils import _parse_chat_message_content
HEADER = (
"x-anthropic-billing-header: cc_version=2.1.220.300; "
File diff suppressed because it is too large Load Diff