Mac M1 Lora Issue?

[ciodelarosa]

On Mac M1, LoRAs are not working. Here is the output I get:

`Loading weights: /path/to/my/LoRA ━━━━━━━━━━━━ 302.1/302.1 0:00:00
MB
12:19:59-790986 ERROR gradio call: RuntimeError
╭───────────────────────────────────────── Traceback (most recent call last) ─────────────────────────────────────────╮
│ /Users/.../automatic/modules/call_queue.py:59 in f │
│ │
│ 58 │ │ │ │ pr.enable() │
│ ❱ 59 │ │ │ res = list(func(*args, **kwargs)) │
│ 60 │ │ │ if shared.cmd_opts.profile: │
│ │
│ /Users/.../automatic/modules/call_queue.py:38 in f │
│ │
│ 37 │ │ │ try: │
│ ❱ 38 │ │ │ │ res = func(*args, **kwargs) │
│ 39 │ │ │ │ progress.record_results(id_task, res) │
│ │
│ ... 26 frames hidden ... │
│ │
│ /Users/.../automatic/extensions-builtin/a1111-sd-webui-lycoris/lycoris.py:740 in lyco_Linear_forward │
│ │
│ 739 │ │
│ ❱ 740 │ return torch.nn.Linear_forward_before_lyco(self, input) │
│ 741 │
│ │
│ /Users/.../automatic/venv/lib/python3.10/site-packages/torch/nn/modules/linear.py:114 in forward │
│ │
│ 113 │ def forward(self, input: Tensor) -> Tensor: │
│ ❱ 114 │ │ return F.linear(input, self.weight, self.bias) │
│ 115 │
╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
RuntimeError: Placeholder storage has not been allocated on MPS device!

`
Thanks so much for your consistent good work!