runs always stucks on INFO 01-12 20:17:39 [base_pipeline.py:343] Scheduler found, paralleling scheduler...

[kazakovaanastasia]

I followed instructions and installed all this way:

Terminal:

mlspace environments create --env name_test --python 3.10 --cuda 12.4
conda activate name_test

Code: (go through Plan):

!pip install xfuser # Basic installation
!pip install "xfuser[diffusers,flash-attn]" # With both diffusers and flash attention
!git clone https://github.com/xdit-project/xDiT.git
cd xDiT
!pip install -e .
'#' Or optionally, with diffusers
!pip install -e ".[diffusers,flash-attn]"

when I run scripts:

!bash examples/run_cogvideo.sh '#' with MODEL_ID in bash script changed to THUDM/CogVideoX1.5-5B

or

!torchrun --nproc_per_node=8
examples/pixartalpha_example.py
--model PixArt-alpha/PixArt-XL-2-1024-MS \ '# ' --model models/PixArt-XL-2-1024-MS
gives an error
--pipefusion_parallel_degree 2
--ulysses_degree 2
--num_inference_steps 20
--warmup_steps 0
--prompt "A cute dog"
--use_cfg_parallel

or (--model PixArt-alpha/PixArt-Sigma-XL-2-1024-MS )

!torchrun --nproc_per_node=8
examples/pixartsigma_example.py
--model PixArt-alpha/PixArt-Sigma-XL-2-1024-MS
--pipefusion_parallel_degree 2
--ulysses_degree 2
--num_inference_steps 20
--warmup_steps 0
--prompt "A cute dog"
--use_cfg_parallel

My run is stucked on line

DEBUG 01-12 20:17:29 [parallel_state.py:179] world_size=-1 rank=-1 local_rank=-1 distributed_init_method=env:// backend=nccl
WARNING 01-12 20:17:29 [args.py:344] Distributed environment is not initialized. Initializing...
...
INFO 01-12 20:17:39 [base_model.py:83] [RANK 6] Wrapping transformer_blocks.41.attn1 in model class CogVideoXTransformer3DModel with xFuserAttentionWrapper
INFO 01-12 20:17:39 [base_pipeline.py:343] Scheduler found, paralleling scheduler...
INFO 01-12 20:17:39 [base_pipeline.py:343] Scheduler found, paralleling scheduler...
INFO 01-12 20:17:39 [base_pipeline.py:343] Scheduler found, paralleling scheduler...

INFO 01-12 20:17:39 [base_pipeline.py:343] Scheduler found, paralleling scheduler...

I waited about 30 minutes - 1 hour with different scripts, and it was still in INFO 01-12 20:17:39 [base_pipeline.py:343] Scheduler found, paralleling scheduler... .