neiltian
neiltian
目前思路是自动生成多语言接口，具体技术还需要调研一下。
@doombeaker I try to find an open source demo. Error related codes: def __getattribute__(self, attribute) (onediff/src/onediff/infer_compiler/transform/builtin_transform.py) elif attribute in ["forward", "_conv_forward"]: replacement = proxy_class(type(self._oflow_proxy_submod)) return lambda *args, **kwargs: getattr(replacement, attribute)(...
@doombeaker https://github.com/MooreThreads/Moore-AnimateAnyone demo has similar errors.
@doombeaker could you tell me, how to fix this issue? first of all, do i need to redefine the corresponding oneflow class and register it based on the register interface?...
error info: TemporalBasicTransformerBlock module's forward interface is hijacked by hacked_basic_transformer_inner_forward.(https://github.com/MooreThreads/Moore-AnimateAnyone/blob/master/src/models/mutual_self_attention.py) does oneflow support this situation？ @strint @doombeaker
@strint @doombeaker TemporalBasicTransformerBlock module's forward is not hijacked(reference_attn is False), oneflow can execute the compile process despite the following error. (https://github.com/MooreThreads/Moore-AnimateAnyone/blob/master/src/models/mutual_self_attention.py) [ERROR](GRAPH:OneflowGraph_1:OneflowGraph) run got error: Cannot find the kernel matching...
> hey,are you trying to use the onediff to accelerate the animate anyone? i'm also working on it. and i find that the torch2.2.0 + torch.compile + cudnn8.6 will speed...
> @strint @doombeaker TemporalBasicTransformerBlock module's forward is not hijacked(reference_attn is False), oneflow can execute the compile process despite the following error. (https://github.com/MooreThreads/Moore-AnimateAnyone/blob/master/src/models/mutual_self_attention.py) ERROR run got error: Cannot find the kernel...
convert failed: Transform failed of : 'function' object has no attribute '' @wangerlie I compile denoising_unet by oneflow_compile. compile_pipe has no acceleration effect, although the above error is not report....
@wangerlie AnimateAnyone pipeline has two unets(denoising_unet and reference_unet). compile_pipe may filter the two unets, this is the onediff filter _PARTS info. _PARTS = [ "text_encoder", "text_encoder_2", "image_encoder", "unet", "controlnet", "fast_unet",...