NotImplementedError: No operator found for memory_efficient_attention_forward with inputs:
query : shape=(8, 1, 8, 64) (torch.float32)
key : shape=(8, 192, 8, 64) (torch.float32)
value : shape=(8, 192, 8, 64) (torch.float32)
attn_bias : <class 'NoneType'>
p : 0.0
[email protected] is not supported because:
requires device with capability < (8, 0) but your GPU has capability (12, 0) (too new)
dtype=torch.float32 (supported: {torch.bfloat16, torch.float16})
requires device with capability == (8, 0) but your GPU has capability (12, 0) (too new)
[email protected] is not supported because:
dtype=torch.float32 (supported: {torch.bfloat16, torch.float16})
cutlassF-pt is not supported because:
requires device with capability < (5, 0) but your GPU has capability (12, 0) (too new)
5070 can not running this function, any help?