A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 12, 08:30 UTC
[Bugfix] Fix wrong mock attribute (#29704)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Nov 29, 2025 at 10:30 UTC
b2c50eda506d0970512e710650d7702e97d19352
1 file changed
+1
-1
tests/entrypoints/openai/test_serving_chat.py
+1
-1
@@ -399,7 +399,7 @@ def _build_serving_chat(engine: AsyncLLM) -> OpenAIServingChat:
399
@dataclass
400
class MockEngine:
401
model_config: MockModelConfig = field(default_factory=MockModelConfig)
402
- processor: MagicMock = field(default_factory=MagicMock)
402
+ input_processor: MagicMock = field(default_factory=MagicMock)
403
io_processor: MagicMock = field(default_factory=MagicMock)
404
405