DeepSeek-V3.2-Exp

        self.qk_head_dim = args.qk_nope_head_dim + args.qk_rope_head_dim
        self.v_head_dim = args.v_head_dim

        self.wq_a = Linear(self.dim, self.q_lora_rank)
        self.q_norm = RMSNorm(self.q_lora_rank)
        self.wq_b = ColumnParallelLinear(self.q_lora_rank, self.n_heads * self.qk_head_dim)
        self.wkv_a = Linear(self.dim, self.kv_lora_rank + self.qk_rope_head_dim)
        self.kv_norm = RMSNorm(self.kv_lora_rank)
        self.wkv_b = ColumnParallelLinear(self.kv_lora_rank, self.n_heads * (self.qk_nope_head_dim + self.v_head_dim))
        self.wo = RowParallelLinear(self.n_heads * self.v_head_dim, self.dim)
        self.softmax_scale = self.qk_head_dim ** -0.5
        self.scale_fmt = args.scale_fmt
        if args.max_seq_len > args.original_seq_len:
            mscale = 0.1 * args.mscale * math.log(args.rope_factor) + 1.0
            self.softmax_scale = self.softmax_scale * mscale * mscale

        self.indexer = Indexer(args)

        qr = self.q_norm(self.wq_a(x))
        q = self.wq_b(qr)
        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)

    def __init__(self, args: ModelArgs):
        super().__init__()
        self.dim: int = args.dim
        self.n_heads: int = args.index_n_heads
        self.n_local_heads = args.index_n_heads // world_size
        self.head_dim: int = args.index_head_dim
        self.rope_head_dim: int = args.qk_rope_head_dim
        self.index_topk: int = args.index_topk
        self.q_lora_rank: int = args.q_lora_rank
        self.wq_b = Linear(self.q_lora_rank, self.n_heads * self.head_dim)
        self.wk = Linear(self.dim, self.head_dim)
        self.k_norm = LayerNorm(self.head_dim)
        # weights_proj in the checkpoint is stored in bf16, while the parameters here are stored in fp32 for convenient.
        self.weights_proj = Linear(self.dim, self.n_heads, dtype=torch.float32)
        self.softmax_scale = self.head_dim ** -0.5
        self.scale_fmt = args.scale_fmt

    def forward(self, x: torch.Tensor, qr: torch.Tensor, start_pos: int, freqs_cis: torch.Tensor, mask: Optional[torch.Tensor]):
        bsz, seqlen, _ = x.size()
        end_pos = start_pos + seqlen
        q = self.wq_b(qr)
        q = q.view(bsz, seqlen, self.n_heads, self.head_dim)
        q_pe, q_nope = torch.split(q, [self.rope_head_dim, self.head_dim - self.rope_head_dim], dim=-1)
        # rope in indexer is not interleaved
        q_pe = apply_rotary_emb(q_pe, freqs_cis, False)
        q = torch.cat([q_pe, q_nope], dim=-1)
        k = self.wk(x)
        k = self.k_norm(k)
        k_pe, k_nope = torch.split(k, [self.rope_head_dim, self.head_dim - self.rope_head_dim], dim=-1)
        # rope in indexer is not interleaved
        k_pe = apply_rotary_emb(k_pe.unsqueeze(2), freqs_cis, False).squeeze(2)
        k = torch.cat([k_pe, k_nope], dim=-1)
        q = rotate_activation(q)
        k = rotate_activation(k)
        q_fp8, q_scale = act_quant(q, block_size, self.scale_fmt)
        k_fp8, k_scale = act_quant(k, block_size, self.scale_fmt)
        self.k_cache[:bsz, start_pos:end_pos] = k_fp8
        self.k_scale_cache[:bsz, start_pos:end_pos] = k_scale
        weights = self.weights_proj(x.float()) * self.n_heads ** -0.5
        weights = weights.unsqueeze(-1) * q_scale * self.softmax_scale
        index_score = fp8_index(q_fp8.contiguous(), weights, self.k_cache[:bsz, :end_pos].contiguous(), self.k_scale_cache[:bsz, :end_pos].contiguous())
        if mask is not None:
            index_score += mask
        topk_indices = index_score.topk(min(self.index_topk, end_pos), dim=-1)[1]
        topk_indices_ = topk_indices.clone()
        dist.broadcast(topk_indices_, src=0)
        assert torch.all(topk_indices == topk_indices_), f"{topk_indices=} {topk_indices_=}"
        return topk_indices

    """
    Perform index score using FP8 precision.

    Args:
        q (torch.Tensor): The Q tensor, must be contiguous.
        q_s (torch.Tensor): The scaling factor for Q (float), must be contiguous.
        k (torch.Tensor): The K tensor, must be contiguous.
        k_s (torch.Tensor): The scaling factor for K (e8m0 here), must be contiguous.

        fp8 q @ fp8 k -> fp32 logits
        relu(fp32 logits) * q_s (weights) -> fp32 logits
        fp32 logits -> fp32 logits_sum
        fp32 logits_sum * k_s (e8m0) -> fp32 index_score
    """