[Core] Consolidate prompt arguments to LLM engines (#4328)

Co-authored-by: Roger Wang <ywang@roblox.com>
This commit is contained in:
Cyrus Leung
2024-05-28 13:29:31 -07:00
committed by GitHub
co-authored by Roger Wang
parent 290f4ada2b
commit 5ae5ed1e60
43 changed files with 1407 additions and 442 deletions
@@ -1,11 +1,15 @@
import asyncio
from dataclasses import dataclass
import pytest
from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
MODEL_NAME = "openai-community/gpt2"
CHAT_TEMPLATE = "Dummy chat template for testing {}"
pytestmark = pytest.mark.openai
@dataclass
class MockModelConfig: