runtime error

Exit code: 1. Reason: models/backbones/internvideo2/flash_attention_class.py", line 6, in <module> from flash_attn.flash_attn_interface import flash_attn_varlen_qkvpacked_func File "/usr/local/lib/python3.10/site-packages/flash_attn/__init__.py", line 3, in <module> from flash_attn.flash_attn_interface import ( File "/usr/local/lib/python3.10/site-packages/flash_attn/flash_attn_interface.py", line 15, in <module> import flash_attn_2_cuda as flash_attn_gpu ModuleNotFoundError: No module named 'flash_attn_2_cuda' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/user/app/app.py", line 85, in <module> video_demo = demo(result_dir) File "/home/user/app/app.py", line 29, in demo text2video = Text2Video(result_dir) File "/home/user/app/demo/t2v.py", line 47, in __init__ viclip_global_instance.instantiate(device='cpu') File "/home/user/app/tools/genrl_utils.py", line 110, in instantiate from small_utils import setup_internvideo2 File "/home/user/app/third_party/InternVideo/InternVideo2/multi_modality/demo/small_utils.py", line 10, in <module> from models.backbones.internvideo2 import pretrain_internvideo2_1b_patch14_224 File "/home/user/app/third_party/InternVideo/InternVideo2/multi_modality/models/__init__.py", line 1, in <module> from .internvideo2_clip import InternVideo2_CLIP File "/home/user/app/third_party/InternVideo/InternVideo2/multi_modality/models/internvideo2_clip.py", line 10, in <module> from .backbones.internvideo2 import InternVideo2, LLaMA, Tokenizer File "/home/user/app/third_party/InternVideo/InternVideo2/multi_modality/models/backbones/internvideo2/__init__.py", line 1, in <module> from .internvl_clip_vision import internvl_clip_6b File "/home/user/app/third_party/InternVideo/InternVideo2/multi_modality/models/backbones/internvideo2/internvl_clip_vision.py", line 14, in <module> from flash_attention_class import FlashAttention ModuleNotFoundError: No module named 'flash_attention_class'

Container logs: