[Frontend][4/n] Improve pooling entrypoints | pooling. (#39153)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-04-09 10:09:45 +00:00
committed by GitHub
parent b6c9be509e
commit 66c079ae83
43 changed files with 554 additions and 733 deletions
-6
View File
@@ -19,7 +19,6 @@ from vllm.logger import init_logger
from vllm.lora.request import LoRARequest
from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
from vllm.outputs import PoolingRequestOutput, RequestOutput
from vllm.plugins.io_processors import get_io_processor
from vllm.pooling_params import PoolingParams
from vllm.renderers import renderer_from_config
from vllm.renderers.inputs.preprocess import extract_prompt_components
@@ -90,11 +89,6 @@ class LLMEngine:
self.should_execute_dummy_batch = False
self.renderer = renderer = renderer_from_config(self.vllm_config)
self.io_processor = get_io_processor(
self.vllm_config,
self.renderer,
self.model_config.io_processor_plugin,
)
# Convert EngineInput --> EngineCoreRequest.
self.input_processor = InputProcessor(self.vllm_config, renderer)