[Bugfix] Validate lora adapters to avoid crashing server (#11727)

Signed-off-by: Joe Runde <Joseph.Runde@ibm.com> Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2025-01-10 00:56:36 -07:00
parent cf5f000d21
commit ac2f3f7fee
15 changed files with 460 additions and 172 deletions
--- a/vllm/entrypoints/openai/run_batch.py
+++ b/vllm/entrypoints/openai/run_batch.py
@@ -215,6 +215,7 @@ async def main(args):

    # Create the openai serving objects.
    openai_serving_models = OpenAIServingModels(
+        engine_client=engine,
        model_config=model_config,
        base_model_paths=base_model_paths,
        lora_modules=None,