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

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 14:46:18 +00:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Christian Pinto
parent fe2016de2d
commit 3fa2c12185
16 changed files with 102 additions and 54 deletions
+1 -6
View File
@@ -1707,11 +1707,6 @@ class IOProcessorRequest(OpenAIBaseModel, Generic[T]):
if the served model does not use priority scheduling.
"""
data: T
"""
When using plugins IOProcessor plugins, the actual input is processed
by the plugin itself. Hence, we use a generic type for the request data
"""
activation: bool = False
encoding_format: EncodingFormat = "float"
embed_dtype: EmbedDType = Field(
@@ -1732,7 +1727,7 @@ class IOProcessorRequest(OpenAIBaseModel, Generic[T]):
)
def to_pooling_params(self):
return PoolingParams(task="token_classify", activation=self.activation)
return PoolingParams()
class IOProcessorResponse(OpenAIBaseModel, Generic[T]):