Skip to content

model

Classes

fastvideo.models.dits.matrixgame2.model.MatrixGame2CrossAttention 

MatrixGame2CrossAttention(dim: int, num_heads: int, window_size=(-1, -1), qk_norm=True, eps=1e-06, parallel_attention=False, quant_config: QuantizationConfig | None = None, prefix: str = '')

Bases: WanSelfAttention

Source code in fastvideo/models/dits/wanvideo.py 
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
def __init__(self,
             dim: int,
             num_heads: int,
             window_size=(-1, -1),
             qk_norm=True,
             eps=1e-6,
             parallel_attention=False,
             quant_config: QuantizationConfig | None = None,
             prefix: str = "") -> None:
    assert dim % num_heads == 0
    super().__init__()
    self.dim = dim
    self.num_heads = num_heads
    self.head_dim = dim // num_heads
    self.window_size = window_size
    self.qk_norm = qk_norm
    self.eps = eps
    self.parallel_attention = parallel_attention

    # layers
    self.to_q = ReplicatedLinear(dim, dim, quant_config=quant_config, prefix=f"{prefix}.to_q")
    self.to_k = ReplicatedLinear(dim, dim, quant_config=quant_config, prefix=f"{prefix}.to_k")
    self.to_v = ReplicatedLinear(dim, dim, quant_config=quant_config, prefix=f"{prefix}.to_v")
    self.to_out = ReplicatedLinear(dim, dim, quant_config=quant_config, prefix=f"{prefix}.to_out")
    self.norm_q = RMSNorm(dim, eps=eps) if qk_norm else nn.Identity()
    self.norm_k = RMSNorm(dim, eps=eps) if qk_norm else nn.Identity()

    # Scaled dot product attention
    self.attn = LocalAttention(
        num_heads=num_heads,
        head_size=self.head_dim,
        dropout_rate=0,
        softmax_scale=None,
        causal=False,
        supported_attention_backends=(AttentionBackendEnum.FLASH_ATTN,
                                      AttentionBackendEnum.TORCH_SDPA))

Methods:

fastvideo.models.dits.matrixgame2.model.MatrixGame2CrossAttention.forward 
forward(x, context, context_lens=None, crossattn_cache=None)

Parameters:

Name Type Description Default
x Tensor

Shape [B, L1, C]

 required
context Tensor

Shape [B, L2, C] - typically 257 image tokens

 required
context_lens Tensor

Shape [B]

 None
crossattn_cache dict

Optional cache for k/v during inference

 None
Source code in fastvideo/models/dits/matrixgame2/model.py 
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
def forward(self, x, context, context_lens=None, crossattn_cache=None):
    r"""
    Args:
        x(Tensor): Shape [B, L1, C]
        context(Tensor): Shape [B, L2, C] - typically 257 image tokens
        context_lens(Tensor): Shape [B]
        crossattn_cache(dict): Optional cache for k/v during inference
    """
    b, n, d = x.size(0), self.num_heads, self.head_dim

    # compute query, key, value
    q = self.norm_q(self.to_q(x)[0]).view(b, -1, n, d)

    if crossattn_cache is not None:
        if not crossattn_cache["is_init"]:
            crossattn_cache["is_init"] = True
            k = self.norm_k(self.to_k(context)[0]).view(b, -1, n, d)
            v = self.to_v(context)[0].view(b, -1, n, d)
            crossattn_cache["k"] = k
            crossattn_cache["v"] = v
        else:
            k = crossattn_cache["k"]
            v = crossattn_cache["v"]
    else:
        k = self.norm_k(self.to_k(context)[0]).view(b, -1, n, d)
        v = self.to_v(context)[0].view(b, -1, n, d)

    # compute attention
    x = self.attn(q, k, v)

    # output
    x = x.flatten(2)
    x, _ = self.to_out(x)
    return x

Functions: