def forward()

in inference/model.py [0:0]

• 40 lines of code
• 6 McCabe index (conditional complexity)

    def forward(self, x: torch.Tensor, start_pos: int, freqs_cis: torch.Tensor, mask: Optional[torch.Tensor]):
        """
        Forward pass for the Multi-Head Latent Attention (MLA) Layer.

        Args:
            x (torch.Tensor): Input tensor of shape (batch_size, seq_len, dim).
            start_pos (int): Starting position in the sequence for caching.
            freqs_cis (torch.Tensor): Precomputed complex exponential values for rotary embeddings.
            mask (Optional[torch.Tensor]): Mask tensor to exclude certain positions from attention.

        Returns:
            torch.Tensor: Output tensor with the same shape as the input.
        """
        bsz, seqlen, _ = x.size()
        end_pos = start_pos + seqlen
        if self.q_lora_rank == 0:
            q = self.wq(x)
        else:
            q = self.wq_b(self.q_norm(self.wq_a(x)))
        q = q.view(bsz, seqlen, self.n_local_heads, self.qk_head_dim)
        q_nope, q_pe = torch.split(q, [self.qk_nope_head_dim, self.qk_rope_head_dim], dim=-1)
        q_pe = apply_rotary_emb(q_pe, freqs_cis)
        kv = self.wkv_a(x)
        kv, k_pe = torch.split(kv, [self.kv_lora_rank, self.qk_rope_head_dim], dim=-1)
        k_pe = apply_rotary_emb(k_pe.unsqueeze(2), freqs_cis)
        if attn_impl == "naive":
            q = torch.cat([q_nope, q_pe], dim=-1)
            kv = self.wkv_b(self.kv_norm(kv))
            kv = kv.view(bsz, seqlen, self.n_local_heads, self.qk_nope_head_dim + self.v_head_dim)
            k_nope, v = torch.split(kv, [self.qk_nope_head_dim, self.v_head_dim], dim=-1)
            k = torch.cat([k_nope, k_pe.expand(-1, -1, self.n_local_heads, -1)], dim=-1)
            self.k_cache[:bsz, start_pos:end_pos] = k
            self.v_cache[:bsz, start_pos:end_pos] = v
            scores = torch.einsum("bshd,bthd->bsht", q, self.k_cache[:bsz, :end_pos]) * self.softmax_scale
        else:
            wkv_b = self.wkv_b.weight if self.wkv_b.scale is None else weight_dequant(self.wkv_b.weight, self.wkv_b.scale, block_size) 
            wkv_b = wkv_b.view(self.n_local_heads, -1, self.kv_lora_rank)
            q_nope = torch.einsum("bshd,hdc->bshc", q_nope, wkv_b[:, :self.qk_nope_head_dim])
            self.kv_cache[:bsz, start_pos:end_pos] = self.kv_norm(kv)
            self.pe_cache[:bsz, start_pos:end_pos] = k_pe.squeeze(2)
            scores = (torch.einsum("bshc,btc->bsht", q_nope, self.kv_cache[:bsz, :end_pos]) +
                      torch.einsum("bshr,btr->bsht", q_pe, self.pe_cache[:bsz, :end_pos])) * self.softmax_scale
        if mask is not None:
            scores += mask.unsqueeze(1)
        scores = scores.softmax(dim=-1, dtype=torch.float32).type_as(x)
        if attn_impl == "naive":
            x = torch.einsum("bsht,bthd->bshd", scores, self.v_cache[:bsz, :end_pos])
        else:
            x = torch.einsum("bsht,btc->bshc", scores, self.kv_cache[:bsz, :end_pos])
            x = torch.einsum("bshc,hdc->bshd", x, wkv_b[:, -self.v_head_dim:])
        x = self.wo(x.flatten(2))
        return x