3060ti上运行很慢

Currently enabled native sdp backends: ['flash', 'math', 'mem_efficient', 'cudnn']
Xformers is not installed!
Flash Attn is not installed!
Sage Attn is not installed!
Namespace(share=False, server='127.0.0.1', port=None, inbrowser=True)
Free VRAM 6.9609375 GB
High-VRAM Mode: False
Downloading shards: 100%|██████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 1996.81it/s]
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 4/4 [00:01<00:00, 2.03it/s]
Fetching 3 files: 100%|████████████████████████████████████████████████████████████████| 3/3 [00:00<00:00, 3000.22it/s]
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 3/3 [00:01<00:00, 1.82it/s]
transformer.high_quality_fp32_output_for_inference = True
* Running on local URL: http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Unloaded DynamicSwap_LlamaModel as complete.
Unloaded CLIPTextModel as complete.
Unloaded SiglipVisionModel as complete.
Unloaded AutoencoderKLHunyuanVideo as complete.
Unloaded DynamicSwap_HunyuanVideoTransformer3DModelPacked as complete.
Loaded CLIPTextModel to cuda:0 as complete.
Unloaded CLIPTextModel as complete.
Loaded AutoencoderKLHunyuanVideo to cuda:0 as complete.
Unloaded AutoencoderKLHunyuanVideo as complete.
Loaded SiglipVisionModel to cuda:0 as complete.
latent_padding_size = 27, is_last_section = False
Unloaded SiglipVisionModel as complete.
Moving DynamicSwap_HunyuanVideoTransformer3DModelPacked to cuda:0 with preserved memory: 6 GB
52%|██████████████████████████████████████████▋ | 13/25 [08:24<04:00, 20.02s/it]

No source files or tests are identified in the report. Start by reproducing the slow run on an RTX 3060 Ti using the provided runtime log, then inspect the attention backends and model-loading behavior; done means identifying and documenting the bottleneck or a reproducible cause.

Written by the indexing model from the issue text.