[Refactor] Pass Renderer to Input Processor (#34329)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2026-02-11 19:38:11 -08:00
committed by GitHub
parent ced2a92f40
commit b96f7314b4
20 changed files with 107 additions and 106 deletions
@@ -157,13 +157,14 @@ class OpenAIServingCompletion(OpenAIServing):
data_parallel_rank = self._get_data_parallel_rank(raw_request)
# Schedule the request and get the result generator.
max_model_len = self.model_config.max_model_len
generators: list[AsyncGenerator[RequestOutput, None]] = []
try:
for i, engine_prompt in enumerate(engine_prompts):
prompt_text = self._extract_prompt_text(engine_prompt)
max_tokens = get_max_tokens(
self.max_model_len,
max_model_len,
request.max_tokens,
self._extract_prompt_len(engine_prompt),
self.default_sampling_params,