Kimi K2

            self.q_a_proj = nn.Linear(
                self.hidden_size, config.q_lora_rank, bias=config.attention_bias
            )
            self.q_a_layernorm = DeepseekV3RMSNorm(config.q_lora_rank)
            self.q_b_proj = nn.Linear(
                config.q_lora_rank, self.num_heads * self.q_head_dim, bias=False
            )

        self.kv_a_proj_with_mqa = nn.Linear(
            self.hidden_size,
            config.kv_lora_rank + config.qk_rope_head_dim,
            bias=config.attention_bias,
        )
        self.kv_a_layernorm = DeepseekV3RMSNorm(config.kv_lora_rank)
        self.kv_b_proj = nn.Linear(
            config.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=config.attention_bias,
        )
        self._init_rope()

        if self.q_lora_rank is None:
            q = self.q_proj(hidden_states)
        else:
            q = self.q_b_proj(self.q_a_layernorm(self.q_a_proj(hidden_states)))
        q = q.view(bsz, q_len, self.num_heads, self.q_head_dim).transpose(1, 2)
        q_nope, q_pe = torch.split(
            q, [self.qk_nope_head_dim, self.qk_rope_head_dim], dim=-1
        )

        cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)

        q_pe, k_pe = apply_rotary_pos_emb(q_pe, k_pe, cos, sin, position_ids)

        query_states = k_pe.new_empty(bsz, self.num_heads, q_len, self.q_head_dim)
        query_states[:, :, :, : self.qk_nope_head_dim] = q_nope
        query_states[:, :, :, self.qk_nope_head_dim :] = q_pe

        key_states = k_pe.new_empty(bsz, self.num_heads, q_len, self.q_head_dim)
        key_states[:, :, :, : self.qk_nope_head_dim] = k_nope
        key_states[:, :, :, self.qk_nope_head_dim :] = k_pe
        if past_key_value is not None:
            cache_kwargs = {"sin": sin, "cos": cos}  # Specific to RoPE models
            key_states, value_states = past_key_value.update(
                key_states, value_states, self.layer_idx, cache_kwargs
            )

        attn_weights = (
            torch.matmul(query_states, key_states.transpose(2, 3)) * self.softmax_scale
        )

        if attn_weights.size() != (bsz, self.num_heads, q_len, kv_seq_len):
            raise ValueError(
                f"Attention weights should be of size {(bsz, self.num_heads, q_len, kv_seq_len)}, but is"
                f" {attn_weights.size()}"
            )
        assert attention_mask is not None
        if attention_mask is not None:
            if attention_mask.size() != (bsz, 1, q_len, kv_seq_len):
                raise ValueError(
                    f"Attention mask should be of size {(bsz, 1, q_len, kv_seq_len)}, but is {attention_mask.size()}"
                )
            attn_weights = attn_weights + attention_mask

        # upcast attention to fp32
        attn_weights = nn.functional.softmax(
            attn_weights, dim=-1, dtype=torch.float32
        ).to(query_states.dtype)
        attn_weights = nn.functional.dropout(
            attn_weights, p=self.attention_dropout, training=self.training
        )
        attn_output = torch.matmul(attn_weights, value_states)

        attn_output = attn_output.transpose(1, 2).contiguous()

        attn_output = attn_output.reshape(bsz, q_len, self.num_heads * self.v_head_dim)

        attn_output = self.o_proj(attn_output)