lora doesn't work when kv_cache is disabled

[ShuaiShao93]

System Info

x86_64, debian 11, L4 gpu

Who can help?

No response

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

1. Install trtllm 0.15.0
2. Build engine with awq int4 and lora, disable kv cache
3. Run TensorRT-LLM/examples/run.py by passing lora dir

Expected behavior

Get results

actual behavior

Segmentation fault

additional notes

N/A