[CORE] Adding support for insertion of soft-tuned prompts (#4645)

Co-authored-by: Swapnil Parekh <swapnilp@ibm.com>
Co-authored-by: Joe G <joseph.granados@h2o.ai>
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>

tests/lora/test_long_context.py

@@ -92,11 +92,10 @@ def batched_generate(
     for input in inputs:
         prompt, sampling_param, lora_req = input
         # Add requests to the engine and run the engine
-        llm._validate_and_add_requests(
-            prompt,
-            sampling_param,
-            lora_request=lora_req,
-        )
+        llm._validate_and_add_requests(prompt,
+                                       sampling_param,
+                                       lora_request=lora_req,
+                                       prompt_adapter_request=None)
 
     outputs = llm._run_engine(use_tqdm=True)
     return [outputs[i].outputs[0].text.strip() for i in range(len(outputs))]