pinokio install get stuck can't install or find dll

[CalmClarity]

C:\Users\Admin\pinokio\api\TRELLIS.git\app>conda_hook && conda deactivate && conda deactivate && conda deactivate && conda activate base && C:\Users\Admin\pinokio\api\TRELLIS.git\app\env\Scripts\activate C:\Users\Admin\pinokio\api
\TRELLIS.git\app\env && python app.py

[SPARSE] Backend: spconv, Attention: flash_attn
Warp 1.5.0 initialized:
CUDA Toolkit 12.6, Driver 12.6
Devices:
"cpu" : "Intel64 Family 6 Model 183 Stepping 1, GenuineIntel"
"cuda:0" : "NVIDIA GeForce RTX 3090" (24 GiB, sm_86, mempool enabled)
"cuda:1" : "NVIDIA GeForce RTX 3090" (24 GiB, sm_86, mempool enabled)
CUDA peer access:
Not supported
Kernel cache:
C:\Users\Admin\AppData\Local\NVIDIA\warp\Cache\1.5.0
C:\Users\Admin\pinokio\api\TRELLIS.git\app\env\lib\site-packages\gradio_client\utils.py:1097: UserWarning: file() is deprecated and will be removed in a future version. Use handle_file() instead.
warnings.warn(
[SPARSE][CONV] spconv algo: auto
[ATTENTION] Using backend: flash_attn
Traceback (most recent call last):
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\app.py", line 246, in
pipeline = TrellisImageTo3DPipeline.from_pretrained("JeffreyXiang/TRELLIS-image-large")
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\trellis\pipelines\trellis_image_to_3d.py", line 55, in from_pretrained
pipeline = super(TrellisImageTo3DPipeline, TrellisImageTo3DPipeline).from_pretrained(path)
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\trellis\pipelines\base.py", line 39, in from_pretrained
models = {
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\trellis\pipelines\base.py", line 40, in
k: models.from_pretrained(f"{path}/{v}")
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\trellis\models_init.py", line 59, in from_pretrained
model = getattr(config['name'])(**config['args'], **kwargs)
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\trellis\models\structured_latent_vae\decoder_mesh.py", line 108, in init
SparseSubdivideBlock3d(
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\trellis\models\structured_latent_vae\decoder_mesh.py", line 43, in init
sp.SparseConv3d(channels, self.out_channels, 3, indice_key=f"res_{self.out_resolution}"),
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\trellis\modules\sparse\conv\conv_spconv.py", line 11, in init
import spconv.pytorch as spconv
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\env\lib\site-packages\spconv_init_.py", line 17, in
from .core import ConvAlgo, AlgoHint
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\env\lib\site-packages\spconv\core.py", line 15, in
from cumm.gemm.main import gen_shuffle_params_v2 as gen_shuffle_params, GemmAlgoParams
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\env\lib\site-packages\cumm\gemm\main.py", line 30, in
from cumm import tensorview as tv
File "C:\Users\Admin\pinokio\api\TRELLIS.git\app\env\lib\site-packages\cumm\tensorview_init_.py", line 27, in
from cumm.core_cc import tensorview_bind
ImportError: DLL load failed while importing core_cc: The specified module could not be found.

(env) (base) C:\Users\Admin\pinokio\api\TRELLIS.git\app>