biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Deprecation] Deprecate code in 0.17 as scheduled (#35441)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Wentao Ye
2026-02-28 12:32:37 -05:00
committed by GitHub
parent 1dafb29f91
commit e113a30113
22 changed files with 31 additions and 250 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
vllm/sampling_params.py
View File

@@ -7,7 +7,7 @@ import json as json_mod
from dataclasses import field
from enum import Enum, IntEnum
from functools import cached_property
from typing import Annotated, Any
from typing import Any
import msgspec
from pydantic.dataclasses import dataclass
@@ -209,10 +209,6 @@ class SamplingParams(
"""Whether to add spaces between special tokens in the output."""
include_stop_str_in_output: bool = False
"""Whether to include the stop strings in output text."""
truncate_prompt_tokens: Annotated[int, msgspec.Meta(ge=-1)] | None = None
"""If set to -1, will use the truncation size supported by the model. If
set to an integer k, will use only the last k tokens from the prompt
(i.e., left truncation). If set to `None`, truncation is disabled."""
output_kind: RequestOutputKind = RequestOutputKind.CUMULATIVE
skip_clone: bool = False
"""Internal flag indicating that this SamplingParams instance is safe to
@@ -273,7 +269,6 @@ class SamplingParams(
detokenize: bool = True,
skip_special_tokens: bool = True,
spaces_between_special_tokens: bool = True,
truncate_prompt_tokens: Annotated[int, msgspec.Meta(ge=-1)] | None = None,
output_kind: RequestOutputKind = RequestOutputKind.CUMULATIVE,
structured_outputs: StructuredOutputsParams | None = None,
logit_bias: dict[int, float] | dict[str, float] | None = None,
@@ -313,7 +308,6 @@ class SamplingParams(
detokenize=detokenize,
skip_special_tokens=skip_special_tokens,
spaces_between_special_tokens=spaces_between_special_tokens,
truncate_prompt_tokens=truncate_prompt_tokens,
output_kind=output_kind,
structured_outputs=structured_outputs,
logit_bias=logit_bias,
@@ -449,15 +443,6 @@ class SamplingParams(
parameter="prompt_logprobs",
value=self.prompt_logprobs,
)
if self.truncate_prompt_tokens is not None and (
self.truncate_prompt_tokens == 0 or self.truncate_prompt_tokens < -1
):
raise VLLMValidationError(
f"truncate_prompt_tokens must be an integer >= 1 or -1, "
f"got {self.truncate_prompt_tokens}",
parameter="truncate_prompt_tokens",
value=self.truncate_prompt_tokens,
)
assert isinstance(self.stop_token_ids, list)
if not all(isinstance(st_id, int) for st_id in self.stop_token_ids):
raise ValueError(
@@ -835,7 +820,6 @@ class SamplingParams(
f"skip_special_tokens={self.skip_special_tokens}, "
"spaces_between_special_tokens="
f"{self.spaces_between_special_tokens}, "
f"truncate_prompt_tokens={self.truncate_prompt_tokens}, "
f"structured_outputs={self.structured_outputs}, "
f"extra_args={self.extra_args})"
)