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

Fix PoolingParams.skip_reading_prefix_cache type (#29364)

Browse Source 
Signed-off-by: KFL <kludev@gmail.com>
This commit is contained in:
kflu
2025-11-24 22:39:29 -08:00
committed by GitHub
parent a21256c463
commit ce58fdc1c3
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/pooling_params.py
View File

@@ -57,7 +57,7 @@ class PoolingParams(
## Internal use only
task: PoolingTask | None = None
requires_token_ids: bool = False
skip_reading_prefix_cache: bool = None
skip_reading_prefix_cache: bool | None = None
extra_kwargs: dict[str, Any] | None = None
output_kind: RequestOutputKind = RequestOutputKind.FINAL_ONLY

2
vllm/sampling_params.py
View File

@@ -238,7 +238,7 @@ class SamplingParams(
generated token can complete the sequence."""
_bad_words_token_ids: list[list[int]] | None = None
skip_reading_prefix_cache: bool = None
skip_reading_prefix_cache: bool | None = None
@staticmethod
def from_optional(