封装VMamba调用

[MPCheng-ZW]

您好！

请问有可以封装好的VMamba可以调用吗？

类似于mamba这种： import torch from mamba_ssm import Mamba

batch, length, dim = 2, 64, 16 x = torch.randn(batch, length, dim).to("cuda") model = Mamba(

This module uses roughly 3 expand d_model^2 parameters

d_model=dim, # Model dimension d_model
d_state=16,  # SSM state expansion factor
d_conv=4,    # Local convolution width
expand=2,    # Block expansion factor

).to("cuda") y = model(x) assert y.shape == x.shape

谢谢~

[MzeroMiko]

There's no pip packages released, and you have to install selective-scan kernel on your own. But we will release the pre-build wheels in the release page soon.