Issues with RunPod

[DanoGL]

I´ve recently moved to RunPod, obviosly Im a dummy, and well.. I´m getting these errors:

This one appears right after I run the "Start Stable Diffusion" cell: Warning: caught exception 'Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 804: forward compatibility was attempted on non supported HW', memory monitor disabled

And this appears when I attempt a generation: Traceback (most recent call last): File "/workspace/sd/stable-diffusion-webui/modules/call_queue.py", line 57, in f res = list(func(*args, kwargs)) File "/workspace/sd/stable-diffusion-webui/modules/call_queue.py", line 37, in f res = func(*args, kwargs) File "/workspace/sd/stable-diffusion-webui/modules/txt2img.py", line 56, in txt2img processed = process_images(p) File "/workspace/sd/stable-diffusion-webui/modules/processing.py", line 515, in process_images res = process_images_inner(p) File "/workspace/sd/stable-diffusion-webui/modules/processing.py", line 658, in process_images_inner uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps step_multiplier, cached_uc) File "/workspace/sd/stable-diffusion-webui/modules/processing.py", line 597, in get_conds_with_caching cache[1] = function(shared.sd_model, required_prompts, steps) File "/workspace/sd/stable-diffusion-webui/modules/prompt_parser.py", line 140, in get_learned_conditioning conds = model.get_learned_conditioning(texts) File "/workspace/sd/stablediffusion/ldm/models/diffusion/ddpm.py", line 669, in get_learned_conditioning c = self.cond_stage_model(c) File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "/workspace/sd/stable-diffusion-webui/modules/sd_hijack_clip.py", line 229, in forward z = self.process_tokens(tokens, multipliers) File "/workspace/sd/stable-diffusion-webui/modules/sd_hijack_clip.py", line 254, in process_tokens z = self.encode_with_transformers(tokens) File "/workspace/sd/stable-diffusion-webui/modules/sd_hijack_clip.py", line 302, in encode_with_transformers outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers) File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "/usr/local/lib/python3.10/dist-packages/transformers/models/clip/modeling_clip.py", line 811, in forward return self.text_model( File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "/usr/local/lib/python3.10/dist-packages/transformers/models/clip/modeling_clip.py", line 721, in forward encoder_outputs = self.encoder( File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "/usr/local/lib/python3.10/dist-packages/transformers/models/clip/modeling_clip.py", line 650, in forward layer_outputs = encoder_layer( File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "/usr/local/lib/python3.10/dist-packages/transformers/models/clip/modeling_clip.py", line 378, in forward hidden_states = self.layer_norm1(hidden_states) File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/normalization.py", line 190, in forward return F.layer_norm( File "/usr/local/lib/python3.10/dist-packages/torch/nn/functional.py", line 2515, in layer_norm return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled) RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'

I have no idea of what could it be, or how can I fix it... Can you guys hel me?

[blckglz110]

+1

[TheLastBen]

that's an issue with the VM, choose a different one by expanding the choices list :

[DanoGL]

that's an issue with the VM, choose a different one by expanding the choices list :

Thanks Ben, once again ❤️