[V0 Deprecation] Remove code related to per-request logits processors (#34400)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-02-12 20:44:28 +08:00
committed by GitHub
parent f5897613fb
commit fb455ed547
12 changed files with 15 additions and 122 deletions
@@ -42,7 +42,6 @@ from vllm.sampling_params import BeamSearchParams, SamplingParams
from vllm.tokenizers import TokenizerLike
from vllm.utils.async_utils import merge_async_iterators
from vllm.utils.collection_utils import as_list
from vllm.v1.sample.logits_processor import validate_logits_processors_parameters
logger = init_logger(__name__)
@@ -67,9 +66,6 @@ class OpenAIServingCompletion(OpenAIServing):
log_error_stack=log_error_stack,
)
# set up logits processors
self.logits_processors = self.model_config.logits_processors
self.enable_prompt_tokens_details = enable_prompt_tokens_details
self.enable_force_include_usage = enable_force_include_usage
@@ -178,13 +174,8 @@ class OpenAIServingCompletion(OpenAIServing):
else:
sampling_params = request.to_sampling_params(
max_tokens,
self.model_config.logits_processor_pattern,
self.default_sampling_params,
)
validate_logits_processors_parameters(
self.logits_processors,
sampling_params,
)
request_id_item = f"{request_id}-{i}"