[Refactor] Call renderer for online IO processor request (#34490)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Cyrus Leung
2026-02-12 22:48:45 -08:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent eea3024f43
commit ec090c2429
4 changed files with 39 additions and 18 deletions
@@ -100,6 +100,18 @@ class IOProcessorRequest(PoolingBasicRequestMixin, EncodingRequestMixin, Generic
data: T
task: PoolingTask = "plugin"
def build_tok_params(self, model_config: ModelConfig) -> TokenizeParams:
encoder_config = model_config.encoder_config or {}
return TokenizeParams(
max_total_tokens=model_config.max_model_len,
max_output_tokens=0,
truncate_prompt_tokens=self.truncate_prompt_tokens,
do_lower_case=encoder_config.get("do_lower_case", False),
add_special_tokens=not model_config.is_encoder_decoder,
max_total_tokens_param="max_model_len",
)
class IOProcessorResponse(OpenAIBaseModel, Generic[T]):
request_id: str | None = None