[Frontend] Refactor prompt processing (#4028)

Co-authored-by: Roger Wang <ywang@roblox.com>
2024-07-23 01:13:53 +08:00
parent 89c1c6a196
commit 739b61a348
24 changed files with 699 additions and 391 deletions
--- a/tests/entrypoints/openai/test_serving_chat.py
+++ b/tests/entrypoints/openai/test_serving_chat.py
@@ -32,7 +32,10 @@ async def _async_serving_chat_init():
                                           model_config,
                                           served_model_names=[MODEL_NAME],
                                           response_role="assistant",
-                                           chat_template=CHAT_TEMPLATE)
+                                           chat_template=CHAT_TEMPLATE,
+                                           lora_modules=None,
+                                           prompt_adapters=None,
+                                           request_logger=None)
    return serving_completion