[Frontend] Delegate tokenization serving preprocessing to OpenAIServingRender (#37266)

Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
2026-03-17 13:22:54 +02:00
parent 4af9ed21cb
commit 00f8e0d211
5 changed files with 33 additions and 30 deletions
--- a/tests/entrypoints/openai/chat_completion/test_chat_error.py
+++ b/tests/entrypoints/openai/chat_completion/test_chat_error.py
@@ -111,7 +111,7 @@ def _build_serving_chat(engine: AsyncLLM) -> OpenAIServingChat:
            [{"prompt_token_ids": [1, 2, 3]}],
        )

-    serving_chat.openai_serving_render._preprocess_chat = AsyncMock(
+    serving_chat.openai_serving_render.preprocess_chat = AsyncMock(
        side_effect=_fake_preprocess_chat
    )
    return serving_chat