Kimi K2

        self.embed_tokens = nn.Embedding(
            config.vocab_size, config.hidden_size, self.padding_idx
        )
        self.layers = nn.ModuleList(
            [
                DeepseekV3DecoderLayer(config, layer_idx)
                for layer_idx in range(config.num_hidden_layers)
            ]
        )
        self._use_flash_attention_2 = config._attn_implementation == "flash_attention_2"
        self.norm = DeepseekV3RMSNorm(config.hidden_size, eps=config.rms_norm_eps)

… lines 1371–1422 omitted …

        past_key_values_length = 0
        if use_cache:
            use_legacy_cache = not isinstance(past_key_values, Cache)
            if use_legacy_cache:
                past_key_values = DynamicCache.from_legacy_cache(past_key_values)
            past_key_values_length = past_key_values.get_usable_length(seq_length)

        if position_ids is None:
            device = input_ids.device if input_ids is not None else inputs_embeds.device
            position_ids = torch.arange(
                past_key_values_length,
                seq_length + past_key_values_length,
                dtype=torch.long,
                device=device,
            )
            position_ids = position_ids.unsqueeze(0)

… lines 1439–1442 omitted …

        if self._use_flash_attention_2:
            # 2d mask is passed through the layers
            attention_mask = (
                attention_mask
                if (attention_mask is not None and 0 in attention_mask)
                else None
            )
        else:
            # 4d mask is passed through the layers
            attention_mask = _prepare_4d_causal_attention_mask(
                attention_mask,
                (batch_size, seq_length),
                inputs_embeds,
                past_key_values_length,
            )

… lines 1458–1521 omitted …

        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)

… lines 1523–1613 omitted …

        hidden_states = outputs[0]
        logits = self.lm_head(hidden_states)
        logits = logits.float()

            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()

        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)