[Frontend][last/5] Improve pooling entrypoints | clean up. (#39675)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-04-16 07:53:23 -07:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 5e5afafa21
commit 4e8c3f1c19
29 changed files with 466 additions and 428 deletions
+14 -13
View File
@@ -9,9 +9,20 @@ from fastapi.responses import JSONResponse, Response, StreamingResponse
from typing_extensions import assert_never
from vllm.entrypoints.openai.engine.protocol import UsageInfo
from vllm.entrypoints.pooling.base.serving import PoolingServing
from vllm.entrypoints.pooling.embed.io_processor import EmbedIOProcessor
from vllm.entrypoints.pooling.embed.protocol import (
from vllm.logger import init_logger
from vllm.outputs import PoolingRequestOutput
from vllm.utils.serial_utils import EmbedDType, Endianness
from ..base.serving import PoolingServing
from ..typing import PoolingServeContext
from ..utils import (
encode_pooling_bytes,
encode_pooling_output_base64,
encode_pooling_output_float,
get_json_response_cls,
)
from .io_processor import EmbedIOProcessor
from .protocol import (
CohereBilledUnits,
CohereEmbedRequest,
CohereEmbedResponse,
@@ -22,16 +33,6 @@ from vllm.entrypoints.pooling.embed.protocol import (
EmbeddingResponseData,
build_typed_embeddings,
)
from vllm.entrypoints.pooling.typing import PoolingServeContext
from vllm.entrypoints.pooling.utils import (
encode_pooling_bytes,
encode_pooling_output_base64,
encode_pooling_output_float,
get_json_response_cls,
)
from vllm.logger import init_logger
from vllm.outputs import PoolingRequestOutput
from vllm.utils.serial_utils import EmbedDType, Endianness
logger = init_logger(__name__)