How fast is the TEXT generation for you? I am getting 0.5 to 1s a line of text? That's SLOW

[GithubStable]

I have these logs:

Load to GPU: CLIPTextModel
Load to GPU: CLIPTextModel
Unload to CPU: CLIPTextModel
Unload to CPU: CLIPTextModel
Load to GPU: UNet2DConditionModel
100%|██████████████████████████████████████████████████████████████████████████████████| 25/25 [00:16<00:00, 1.56it/s]
Unload to CPU: UNet2DConditionModel
Load to GPU: AutoencoderKL
Unload to CPU: AutoencoderKL
You shouldn't move a model that is dispatched using accelerate hooks.
Load to GPU: LlamaForCausalLM
The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's attention_mask to obtain reliable results.
Setting pad_token_id to eos_token_id:128001 for open-end generation.

Wonder if I have any problem, or is it supposed to be THAT slow?
Please tell me how fast the prompt generations are for you please,
For me it's like Half to One second per line of text, and each prompt has like 20-40 lines, that's quite slow to generate a prompt, am I missing something?