Commit 725cc729 authored by justheuristic's avatar justheuristic
Browse files

cast device

parent 28a9313d
......@@ -567,7 +567,7 @@ def test_linear8bitlt_no_fp16_weights(threshold, memory_efficient_backward):
mlp.zero_grad()
(o1 * grad_proj).sum().backward()
grad_ref = grad_proj.flatten(2) @ w2.to() @ w1.to(grad_proj.device)
grad_ref = grad_proj.flatten(2) @ w2 @ w1
assert torch.allclose(b1.grad, grad_ref)
......
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