Commit b49d3f59 authored by Your Name's avatar Your Name

Fix deprecation: torch_dtype -> dtype

parent ba4ce29f
......@@ -277,9 +277,9 @@ class NvidiaBackend(ModelBackend):
print("Warning: bitsandbytes not installed. Quantization disabled.")
if self.device == "cuda":
load_kwargs['torch_dtype'] = torch.float16
load_kwargs['dtype'] = torch.float16
else:
load_kwargs['torch_dtype'] = torch.float32
load_kwargs['dtype'] = torch.float32
if offload_dir:
os.makedirs(offload_dir, exist_ok=True)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment