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 14, 05:30 UTC
[Bugfix] Fix test_lora_resolvers.py (#23984)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Jee Jee Li committed
Aug 30, 2025 at 19:16 UTC
628d00cd7b06c9706b0613aafaefe927fb255877
1 file changed
+1
tests/entrypoints/openai/test_lora_resolvers.py
+1
@@ -47,6 +47,7 @@ class MockModelConfig:
47
allowed_local_media_path: str = ""
48
encoder_config = None
49
generation_config: str = "auto"
50
+ skip_tokenizer_init: bool = False
51
52
def get_diff_sampling_param(self):
53
return self.diff_sampling_param or {}