MCPcopy Create free account
hub / github.com/MotrixLab/ViMoGen / forward

Method forward

models/transformer/wan/modules/tm2m_model.py:513–518  ·  view source on GitHub ↗
(self, x, e)

Source from the content-addressed store, hash-verified

511 self.modulation = nn.Parameter(torch.randn(1, 2, dim) / dim**0.5)
512
513 def forward(self, x, e):
514 assert e.dtype == torch.float32
515 with amp.autocast(dtype=torch.float32, device_type="cuda"):
516 e = (self.modulation.to(dtype=e.dtype, device=e.device) + e.unsqueeze(1)).chunk(2, dim=1)
517 x = (self.head(self.norm(x) * (1 + e[1]) + e[0]))
518 return x
519
520
521class MLPProj(torch.nn.Module):

Callers 1

forwardMethod · 0.45

Calls

no outgoing calls

Tested by

no test coverage detected