[Bug]: getattr used on dict for rope_scaling config, leading to incorrect factor

[RobertLou]

System Info

TensorRT-LLM main

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

In https://github.com/NVIDIA/TensorRT-LLM/blob/main/tensorrt_llm/_torch/modules/qk_norm_attention.py
line 58:
factor = getattr(rope_scaling, "factor", 1.0)
rope_scaling is a dict, so "factor" will always be 1.0.

Expected behavior

None

actual behavior

None

additional notes

None

Before submitting a new issue...

• Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

[RobertLou]

Should I submit a PR for this one-line change?

[RobertLou]

Same Problem with line 48:
if rope_scaling is None or getattr(rope_scaling, "rope_type", None) != "yarn":

[karljang]

Could you make a pr to fix those issues~? Thank you!