Can't run in ArchLinux with RTX 5050

Trying to run in my laptop, but no success. Here are the command I inputed and the output messages

```
🐍 seedvr  vinicius@ArchLinux  ~/SeedVR   main  torchrun \
--nproc-per-node=1 \
projects/inference_seedvr2_3b.py \
--video_path /home/vinicius/Vídeos/input \
--output_dir /home/vinicius/Vídeos/processed \
--seed 42 \
--res_h 1080 \
--res_w 1920 \
--sp_size 4
/home/vinicius/SeedVR
/home/vinicius/.conda/envs/seedvr/lib/python3.10/site-packages/torch/cuda/__init__.py:209: UserWarning:
NVIDIA GeForce RTX 5050 Laptop GPU with CUDA capability sm_120 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_50 sm_60 sm_70 sm_75 sm_80 sm_86 sm_90.
If you want to use the NVIDIA GeForce RTX 5050 Laptop GPU GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/

warnings.warn(
2026-01-13 07:31:38,235 [MainThread][common.decorators][INFO] Entering configure_dit_model
/home/vinicius/.conda/envs/seedvr/lib/python3.10/site-packages/pyramid/path.py:3: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
import pkg_resources
[rank0]: Traceback (most recent call last):
[rank0]: File "/home/vinicius/SeedVR/projects/inference_seedvr2_3b.py", line 336, in
[rank0]: runner = configure_runner(args.sp_size)
[rank0]: File "/home/vinicius/SeedVR/projects/inference_seedvr2_3b.py", line 77, in configure_runner
[rank0]: runner.configure_dit_model(device="cuda", checkpoint='./ckpts/seedvr2_ema_3b.pth')
[rank0]: File "/home/vinicius/SeedVR/common/decorators.py", line 39, in log_on_entry_wrapper
[rank0]: return func(*args, **kwargs)
[rank0]: File "/home/vinicius/SeedVR/common/decorators.py", line 142, in wrapped
[rank0]: result = func(*args, **kwargs)
[rank0]: File "/home/vinicius/SeedVR/projects/video_diffusion_sr/infer.py", line 85, in configure_dit_model
[rank0]: self.dit = create_object(self.config.dit.model)
[rank0]: File "/home/vinicius/SeedVR/common/config.py", line 109, in create_object
[rank0]: return item(**config)
[rank0]: File "/home/vinicius/SeedVR/models/dit_v2/nadit.py", line 135, in __init__
[rank0]: [
[rank0]: File "/home/vinicius/SeedVR/models/dit_v2/nadit.py", line 136, in
[rank0]: get_nablock(block_type[i])(
[rank0]: File "/home/vinicius/SeedVR/models/dit_v2/nablocks/mmsr_block.py", line 54, in __init__
[rank0]: self.attn_norm = MMModule(norm, dim=dim, eps=norm_eps, elementwise_affine=False, shared_weights=shared_weights,)
[rank0]: File "/home/vinicius/SeedVR/models/dit_v2/mm.py", line 52, in __init__
[rank0]: self.vid = module(*get_args("vid", args), **get_kwargs("vid", kwargs))
[rank0]: File "/home/vinicius/SeedVR/models/dit_v2/normalization.py", line 53, in _norm_layer
[rank0]: from apex.normalization import FusedRMSNorm
[rank0]: File "/home/vinicius/.conda/envs/seedvr/lib/python3.10/site-packages/apex/__init__.py", line 13, in
[rank0]: from pyramid.session import UnencryptedCookieSessionFactoryConfig
[rank0]: ImportError: cannot import name 'UnencryptedCookieSessionFactoryConfig' from 'pyramid.session' (unknown location)
E0113 07:34:10.481000 139738037990656 torch/distributed/elastic/multiprocessing/api.py:826] failed (exitcode: 1) local_rank: 0 (pid: 245000) of binary: /home/vinicius/.conda/envs/seedvr/bin/python3.10
Traceback (most recent call last):
File "/home/vinicius/.conda/envs/seedvr/bin/torchrun", line 7, in
sys.exit(main())
File "/home/vinicius/.conda/envs/seedvr/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 347, in wrapper
return f(*args, **kwargs)
File "/home/vinicius/.conda/envs/seedvr/lib/python3.10/site-packages/torch/distributed/run.py", line 879, in main
run(args)
File "/home/vinicius/.conda/envs/seedvr/lib/python3.10/site-packages/torch/distributed/run.py", line 870, in run
elastic_launch(
File "/home/vinicius/.conda/envs/seedvr/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 132, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/home/vinicius/.conda/envs/seedvr/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 263, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
projects/inference_seedvr2_3b.py FAILED
------------------------------------------------------------
Failures:

------------------------------------------------------------
Root Cause (first observed failure):
[0]:
time : 2026-01-13_07:34:10
host : localhost
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 245000)
error_file:
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
============================================================

```

I installed the conda environment exactly as instructed, except in flash_attn part, whose compilation didn't work. I downloaded and installed a pre-compiled wheel and installed with pip install `/home/vinicius/Downloads/flash_attn-2.5.9+cu121torch2.3-cp310-cp310-linux_x86_64.whl`