CUDA Setup failed despite GPU being available

[whmc76]

got prompt
[rgthree] Using rgthree's optimized recursive execution.
[rgthree] First run patching recursive_output_delete_if_changed and recursive_will_execute.
[rgthree] Note: If execution seems broken due to forward ComfyUI changes, you can disable the optimization from rgthree settings in ComfyUI.
The config attributes {'decay': 0.9999, 'inv_gamma': 1.0, 'min_decay': 0.0, 'optimization_step': 37000, 'power': 0.6666666666666666, 'update_after_step': 0, 'use_ema_warmup': False} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
Some weights of the model checkpoint were not used when initializing UNet2DConditionModel:
['add_embedding.linear_1.bias, add_embedding.linear_1.weight, add_embedding.linear_2.bias, add_embedding.linear_2.weight']
Loading pipeline components...: 0%| | 0/8 [00:00<?, ?it/s]False

===================================BUG REPORT===================================
E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\cuda_setup\main.py:167: UserWarning: Welcome to bitsandbytes. For bug reports, please run

python -m bitsandbytes

warn(msg)

CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
The following directories listed in your path were found to be non-existent: {WindowsPath('/usr/local/cuda/lib64')}
DEBUG: Possible options found for libcudart.so: set()
CUDA SETUP: PyTorch settings found: CUDA_VERSION=121, Highest Compute Capability: 8.9.
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
CUDA SETUP: Loading binary E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\libbitsandbytes_cuda121.so...
argument of type 'WindowsPath' is not iterable
CUDA SETUP: Problem: The main issue seems to be that the main CUDA runtime library was not detected.
CUDA SETUP: Solution 1: To solve the issue the libcudart.so location needs to be added to the LD_LIBRARY_PATH variable
CUDA SETUP: Solution 1a): Find the cuda runtime library via: find / -name libcudart.so 2>/dev/null
CUDA SETUP: Solution 1b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_1a
CUDA SETUP: Solution 1c): For a permanent solution add the export from 1b into your .bashrc file, located at ~/.bashrc
CUDA SETUP: Solution 2: If no library was found in step 1a) you need to install CUDA.
CUDA SETUP: Solution 2a): Download CUDA install script: wget https://raw.githubusercontent.com/TimDettmers/bitsandbytes/main/cuda_install.sh
CUDA SETUP: Solution 2b): Install desired CUDA version to desired location. The syntax is bash cuda_install.sh CUDA_VERSION PATH_TO_INSTALL_INTO.
CUDA SETUP: Solution 2b): For example, "bash cuda_install.sh 113 ~/local/" will download CUDA 11.3 and install into the folder ~/local
Loading pipeline components...: 0%| | 0/8 [00:00<?, ?it/s]
!!! Exception during processing!!!
CUDA Setup failed despite GPU being available. Please run the following command to get more information:

    python -m bitsandbytes

    Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
    to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
    and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues

Traceback (most recent call last):
File "E:\IMAGE\ComfyUI_master\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\ComfyUI\custom_nodes\ComfyUI-IDM-VTON\src\nodes\pipeline_loader.py", line 96, in load_pipeline
pipe = TryonPipeline.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\huggingface_hub\utils_validators.py", line 118, in inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 812, in from_pretrained
maybe_raise_or_warn(
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\diffusers\pipelines\pipeline_loading_utils.py", line 254, in maybe_raise_or_warn
unwrapped_sub_model = unwrap_model(sub_model)
^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\diffusers\pipelines\pipeline_loading_utils.py", line 229, in unwrap_model
from peft import PeftModel
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\peft_init.py", line 22, in
from .auto import (
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\peft\auto.py", line 31, in
from .config import PeftConfig
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\peft\config.py", line 23, in
from .utils import CONFIG_NAME, PeftType, TaskType
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\peft\utils_init.py", line 21, in
from .loftq_utils import replace_lora_weights_loftq
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\peft\utils\loftq_utils.py", line 35, in
import bitsandbytes as bnb
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes_init.py", line 6, in
from . import cuda_setup, utils, research
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\research_init_.py", line 1, in
from . import nn
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\research\nn_init_.py", line 1, in
from .modules import LinearFP8Mixed, LinearFP8Global
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\research\nn\modules.py", line 8, in
from bitsandbytes.optim import GlobalOptimManager
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\optim_init_.py", line 6, in
from bitsandbytes.cextension import COMPILED_WITH_CUDA
File "E:\IMAGE\ComfyUI_master\python_embeded\Lib\site-packages\bitsandbytes\cextension.py", line 20, in
raise RuntimeError('''
RuntimeError:
CUDA Setup failed despite GPU being available. Please run the following command to get more information:

    python -m bitsandbytes

    Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
    to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
    and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues

[profiler] #11 PipelineLoader: 23.8465 seconds, total 23.8465 seconds
[profiler] #10 IDM-VTON: 0.001 seconds, total 23.8474 seconds(#11 #14 #13 #16 #17)
[profiler] #18 SaveImage: 0.0006 seconds, total 23.848 seconds(#10)
Prompt executed in 23.85 seconds

[Poukpalaova]

I got same error. It doesn't give me this error when on BF16 but got out of memory error try to request 6mb when i have 24gb free lol.