2080ti魔改22G，报错，求解

[zhai-hello]

Error occurred when executing KSamplerTheMisto:

No operator found for memory_efficient_attention_forward with inputs:
query : shape=(24, 4352, 1, 128) (torch.bfloat16)
key : shape=(24, 4352, 1, 128) (torch.bfloat16)
value : shape=(24, 4352, 1, 128) (torch.bfloat16)
attn_bias :
p : 0.0
decoderF is not supported because:
attn_bias type is
bf16 is only supported on A100+ GPUs
flshattF@v2.5.7 is not supported because:
requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old)
bf16 is only supported on A100+ GPUs
cutlassF is not supported because:
bf16 is only supported on A100+ GPUs
smallkF is not supported because:
max(query.shape[-1] != value.shape[-1]) > 32
dtype=torch.bfloat16 (supported: {torch.float32})
bf16 is only supported on A100+ GPUs
unsupported embed per head: 128

[baizh0u]

更新插件，可能会修复问题，但是你这个魔改的显卡未必能跑。

[zhai-hello]

从别处看到的解决方法，试了一下，果然可以了。[MistoControlNet-Flux-dev]这个效果很不错，大家都给作者点star
具体方式是：我用的秋叶启动包，点击左侧高级选项，然后cross-attention 优化方案修改成使用缩放积点SDP方案，就可以了。