mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2026-01-11 08:04:28 +08:00
799397ee4f
Signed-off-by: Max de Bayser <mbayser@br.ibm.com> Signed-off-by: Max de Bayser <maxdebayser@gmail.com> Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com> Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
62 lines
2.3 KiB
Python
62 lines
2.3 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
from typing import TYPE_CHECKING, Any, Optional
|
|
|
|
import msgspec
|
|
|
|
from vllm.sampling_params import RequestOutputKind
|
|
|
|
if TYPE_CHECKING:
|
|
from vllm.config import ModelConfig
|
|
|
|
|
|
class PoolingParams(
|
|
msgspec.Struct,
|
|
omit_defaults=True, # type: ignore[call-arg]
|
|
array_like=True): # type: ignore[call-arg]
|
|
"""API parameters for pooling models. This is currently a placeholder.
|
|
|
|
Attributes:
|
|
dimensions: Reduce the dimensions of embeddings
|
|
if model support matryoshka representation.
|
|
additional_data: Any additional data needed for pooling.
|
|
"""
|
|
|
|
dimensions: Optional[int] = None
|
|
additional_data: Optional[Any] = None
|
|
output_kind: RequestOutputKind = RequestOutputKind.FINAL_ONLY
|
|
|
|
def clone(self) -> "PoolingParams":
|
|
"""Returns a deep copy of the PoolingParams instance."""
|
|
return PoolingParams(dimensions=self.dimensions,
|
|
additional_data=self.additional_data)
|
|
|
|
def verify(self, model_config: "ModelConfig") -> None:
|
|
if self.dimensions is not None:
|
|
if not model_config.is_matryoshka:
|
|
raise ValueError(
|
|
f'Model "{model_config.served_model_name}" does not '
|
|
f'support matryoshka representation, '
|
|
f'changing output dimensions will lead to poor results.')
|
|
|
|
mds = model_config.matryoshka_dimensions
|
|
if mds is not None:
|
|
if self.dimensions not in mds:
|
|
raise ValueError(
|
|
f'Model "{model_config.served_model_name}" '
|
|
f'only supports {str(mds)} matryoshka dimensions, '
|
|
f'use other output dimensions will '
|
|
f'lead to poor results.')
|
|
elif self.dimensions < 1:
|
|
raise ValueError("Dimensions must be greater than 0")
|
|
|
|
def __repr__(self) -> str:
|
|
return (f"PoolingParams("
|
|
f"dimensions={self.dimensions}, "
|
|
f"additional_metadata={self.additional_data})")
|
|
|
|
def __post_init__(self) -> None:
|
|
assert self.output_kind == RequestOutputKind.FINAL_ONLY,\
|
|
"For pooling output_kind has to be FINAL_ONLY"
|