fanty

Why the code for Wan2.1 uses t_mod to determine whether to cache rather than using timestep embedding?

5

> Hi, [@zishen-ucap](https://github.com/zishen-ucap). Your observation is right. For some model, timestep embedding shows better correlation, e.g., Wan2.1 and CogVideoX. With timestep embedding before 'time_projection', it is unnecessary to to set...

Why is sage_attn2 disabled on H100 with CPU offload?

5

Found this restriction in the code: https://github.com/ModelTC/LightX2V/blob/4f3534923b64cc4fb3b7bbb8343fa224737ee6b5/lightx2v/models/networks/wan/infer/transformer_infer.py#L39 Why is sage_attn2 incompatible with H100 (compute capability 9.0) + CPU offload? Thank you for your time! Could you please explain the reasoning...