TensorRT Extension problem : Entry Point Not Found

[ccarmatic]

CUDA 11.8, Python 3.10.14, Windows 11
Installed as per instructions:
pip3 install torch==2.1.0 torchvision==0.16.0 xformers --index-url https://download.pytorch.org/whl/cu118
pip install git+https://github.com/cumulo-autumn/StreamDiffusion.git@main#egg=streamdiffusion[tensorrt]
python -m streamdiffusion.tools.install-tensorrt

I have a Python script which contains:

import torch
from diffusers import AutoencoderTiny, StableDiffusionPipeline
from streamdiffusion import StreamDiffusion
from streamdiffusion.acceleration.tensorrt import accelerate_with_tensorrt
BATCH_SIZE = 1
WIDTH, HEIGHT = 512,512
TORCH_DEVICE  = 'cuda' # "cuda" if you have a cuda GPU
TORCH_DTYPE   = torch.float16

model_loc = "models/LCM_Dreamshaper_v7"
pipe = StableDiffusionPipeline.from_pretrained(model_loc).to(
    device=torch.device(TORCH_DEVICE),
    dtype=TORCH_DTYPE,
)
stream = StreamDiffusion(
    pipe,
    t_index_list=[32,45],
    torch_dtype=TORCH_DTYPE,
    frame_buffer_size=BATCH_SIZE,
    width=WIDTH,
    height=HEIGHT,
    do_add_noise=True,
    cfg_type='none'
)
stream = accelerate_with_tensorrt(
    stream, "engines", max_batch_size=BATCH_SIZE,
)

Running it results in this:

4 windows sequentially opening, about the following dll files:

cudnn_adv_infer64_8.dll
cudnn_adv_train64_8.dll
cudnn_cnn_infer64_8.dll
cudnn_cnn_train64_8.dll