Disable autocast for cpu to fix error. Remove unused precision arg. (#518)

When running on just cpu (intel), a call to torch.layer_norm would error with RuntimeError: expected scalar type BFloat16 but found Float
Fix buggy device handling in model.py.
Tested with scripts/dream.py --full_precision on just cpu on intel laptop. Works but slow at ~10s/it.

ldm/dream/devices.py

@@ -13,8 +13,9 @@ def choose_torch_device() -> str:
 def choose_autocast_device(device):
     '''Returns an autocast compatible device from a torch device'''
     device_type = device.type # this returns 'mps' on M1
-    # autocast only supports cuda or cpu
-    if device_type in ('cuda','cpu'):
+    if device_type == 'cuda':
         return device_type,autocast
+    elif device_type == 'cpu':
+        return device_type,nullcontext
     else:
         return 'cpu',nullcontext

ldm/generate.py

@@ -111,7 +111,6 @@ class Generate:
             height                = 512,
             sampler_name          = 'k_lms',
             ddim_eta              = 0.0,  # deterministic
-            precision             = 'autocast',
             full_precision        = False,
             strength              = 0.75,  # default in scripts/img2img.py
             seamless              = False,
@@ -129,7 +128,6 @@ class Generate:
         self.sampler_name             = sampler_name
         self.grid                     = grid
         self.ddim_eta                 = ddim_eta
-        self.precision                = precision
         self.full_precision           = True if choose_torch_device() == 'mps' else full_precision
         self.strength                 = strength
         self.seamless                 = seamless

ldm/modules/diffusionmodules/model.py

@@ -209,8 +209,7 @@ class AttnBlock(nn.Module):
 
         h_ = torch.zeros_like(k, device=q.device)
 
-        device_type = 'mps' if q.device.type == 'mps' else 'cuda'
-        if device_type == 'cuda':
+        if q.device.type == 'cuda':
             stats = torch.cuda.memory_stats(q.device)
             mem_active = stats['active_bytes.all.current']
             mem_reserved = stats['reserved_bytes.all.current']
@@ -612,9 +611,8 @@ class Decoder(nn.Module):
         del h3
 
         # prepare for up sampling
-        device_type = 'mps' if h.device.type == 'mps' else 'cuda'
         gc.collect()
-        if device_type == 'cuda':
+        if h.device.type == 'cuda':
             torch.cuda.empty_cache()
 
         # upsampling