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

[Frontend][4/N] Improve all pooling task | Add plugin pooling task (#26973)

Browse Source 
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Christian Pinto <christian.pinto@ibm.com>
This commit is contained in:
wang.yuqi
2025-10-23 22:46:18 +08:00
committed by GitHub
parent fe2016de2d
commit 3fa2c12185
16 changed files with 102 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
vllm/entrypoints/openai/serving_pooling.py
View File

@@ -32,7 +32,7 @@ from vllm.entrypoints.renderer import RenderConfig
from vllm.entrypoints.utils import _validate_truncation_size
from vllm.logger import init_logger
from vllm.outputs import PoolingRequestOutput
from vllm.tasks import SupportedTask
from vllm.tasks import PoolingTask, SupportedTask
from vllm.utils.async_utils import merge_async_iterators
from vllm.utils.serial_utils import (
EmbedDType,
@@ -161,12 +161,21 @@ class OpenAIServingPooling(OpenAIServing):
# Schedule the request and get the result generator.
generators: list[AsyncGenerator[PoolingRequestOutput, None]] = []
try:
pooling_params = request.to_pooling_params()
if is_io_processor_request:
assert self.io_processor is not None and isinstance(
request, IOProcessorRequest
)
pooling_params = self.io_processor.validate_or_generate_params()
else:
pooling_params = request.to_pooling_params()
pooling_task: PoolingTask
if "token_embed" in self.supported_tasks:
pooling_task = "token_embed"
elif "token_classify" in self.supported_tasks:
pooling_task = "token_classify"
elif "plugin" in self.supported_tasks:
pooling_task = "plugin"
else:
return self.create_error_response(
f"pooling_task must be one of {self.supported_tasks}."