search

NVIDIA / TensorRT-Model-Optimizer

TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.
https://nvidia.github.io/TensorRT-Model-Optimizer
Other
574 stars 43 forks source link

cross_attention_kwargs ['adapter_params'] are not expected by DefaultAttnProcessor2_0 and will be ignored. #93

Open zeng121 opened 1 month ago

zeng121 commented 1 month ago

When I use Ipadpter in cache_diffusion, it doesn't work and prints the following message in the terminal

cross_attention_kwargs ['adapter_params'] are not expected by DefaultAttnProcessor2_0 and will be ignored.

Edwardf0t1 commented 2 weeks ago

@zeng121 could you please share the steps and envs you use to reproduce the issue?