Vchitect-XL

import torch
from diffusers import CogView4Pipeline
from diffusers.hooks import apply_first_block_cache, FirstBlockCacheConfig

pipe = CogView4Pipeline.from_pretrained("THUDM/CogView4-6B", torch_dtype=torch.bfloat16)
pipe.to("cuda")

apply_first_block_cache(pipe.transformer, FirstBlockCacheConfig(threshold=0.2))

prompt = "A photo of an astronaut riding a horse on mars"
image = pipe(prompt, generator=torch.Generator().manual_seed(42)).images[0]
image.save("output.png")

import torch
from torch._functorch.partitioners import draw_graph

def compiler(fx_module: torch.fx.GraphModule, _):
    draw_graph(fx_module, f"compile.dot")
    return fx_module.forward

def capture(model, *inputs):
    compiled_model = torch.compile(model, backend=compiler)
    y = compiled_model(*inputs)
    y.sum().backward()

class MLP(torch.nn.Module):
    def __init__(self):
        super().__init__()
        
        self.linear_1 = torch.nn.Linear(16, 32)
        self.linear_2 = torch.nn.Linear(32, 16)
    
    def forward(self, x):
        x = self.linear_1(x)
        x = torch.nn.functional.silu(x)
        x = self.linear_2(x)
        return x

if __name__ == '__main__':
    model = MLP()
    model.to("mps")
    x = torch.randn(4, 16, device="mps", dtype=torch.float32)

    capture(model, x)