Kimi K3

def eager_attention_forward(
    module: nn.Module,
    query: torch.Tensor,
    key: torch.Tensor,
    value: torch.Tensor,
    attention_mask: torch.Tensor | None,
    scaling: float,
    dropout: float = 0.0,
    **kwargs: Unpack[TransformersKwargs],
):
    key = repeat_kv(key, module.num_key_value_groups)
    value = repeat_kv(value, module.num_key_value_groups)

    scores = torch.einsum("bhqd,bhkd->bhqk", query, key) * scaling
    if attention_mask is not None:
        scores = scores + attention_mask[:, :, :, : key.shape[-2]]

    probs = F.softmax(scores, dim=-1, dtype=torch.float32).to(query.dtype)
    probs = F.dropout(probs, p=dropout, training=module.training)
    out = torch.einsum("bhqk,bhkd->bhqd", probs, value).transpose(1, 2).contiguous()

    return out, probs

… lines 333–449 omitted …

        attention_interface: Callable = eager_attention_forward
        if self.config._attn_implementation != "eager":
            attention_interface = ALL_ATTENTION_FUNCTIONS[self.config._attn_implementation]

        attn_output, _ = attention_interface(
            self,
            query_states,
            key_states,
            value_states,
            attention_mask,
            dropout=0.0 if not self.training else self.attention_dropout,
            scaling=self.scaling,
            **kwargs,
        )

    def __init__(self, config: KimiLinearConfig, layer_idx: int):
        nn.Module.__init__(self)
        self.config = config
        self.layer_idx = layer_idx
        self.hidden_size = config.hidden_size
        self.num_heads = config.num_attention_heads
        self.num_key_value_heads = config.num_key_value_heads
        self.num_key_value_groups = self.num_heads // self.num_key_value_heads

        self.attention_dropout = getattr(config, "attention_dropout", 0.0)

        try:
            self.q_lora_rank = config.q_lora_rank
            self.qk_rope_head_dim = config.qk_rope_head_dim
            self.kv_lora_rank = config.kv_lora_rank
            self.v_head_dim = config.v_head_dim
            self.qk_nope_head_dim = config.qk_nope_head_dim
            self.q_head_dim = self.qk_nope_head_dim + self.qk_rope_head_dim
            self.use_nope = config.mla_use_nope
            self.scaling = self.q_head_dim ** (-0.5)
        except Exception as e:
            raise ValueError(
                f"Kimi MLA config is not found or not properly formatted: {e}")

        if self.q_lora_rank is not None:
            self.q_a_proj = nn.Linear(
                self.hidden_size, self.q_lora_rank, bias=False,
            )
            self.q_a_layernorm = KimiRMSNorm(self.q_lora_rank)
            self.q_b_proj = nn.Linear(
                self.q_lora_rank,
                self.num_heads * self.q_head_dim,
                bias=False,
            )
        else:
            self.q_proj = nn.Linear(
                self.hidden_size, self.num_heads * self.q_head_dim, bias=False,
            )
        self.kv_a_proj_with_mqa = nn.Linear(
            self.hidden_size,
            self.kv_lora_rank + self.qk_rope_head_dim,
            bias=False,
        )
        self.kv_a_layernorm = KimiRMSNorm(self.kv_lora_rank)
        self.kv_b_proj = nn.Linear(
            self.kv_lora_rank,
            self.num_heads
            * (self.q_head_dim - self.qk_rope_head_dim + self.v_head_dim),
            bias=False,
        )
        self.o_proj = nn.Linear(
            self.num_heads * self.v_head_dim,
            self.hidden_size,
            bias=False,
        )
        self.is_causal = True
        assert self.use_nope

        self.use_output_gate = getattr(config, "mla_use_output_gate", False)
        if self.use_output_gate:
            projection_size = self.num_heads * self.v_head_dim
            self.g_proj = nn.Linear(self.hidden_size, projection_size, bias=False)

        self.rotary_emb = None

        attn_output = attn_output.reshape(
            batch_size, seq_length, -1).contiguous()
        if self.use_output_gate:
            g = self.g_proj(hidden_states).sigmoid()
            attn_output = attn_output * g
        attn_output = self.o_proj(attn_output)
        return attn_output