DeepSeek-V3.2-Exp · Cached latents

61 transformer blocks › 58 MoE blocks › Sparse latent attention › Sparse attention › Mix and project

Cached latents

supplied · no parametersv

128 value heads.

shape: $\hat c^{KV}$ [B batch, 1001 cached positions, 512 kv latent]

Sources

Contextual evidence from KV cache

MLA keeps two buffers per layer, allocated for max_seq_len positions: the normalized key–value latent and the rotary key; each call writes its positions, rounding the latent through FP8 first.

mla-cache · deepseek-ai/DeepSeek-V3.2-Exp / inference/model.py
Pinned revision 87e509a2e5a1 ↗ · lines 541–573

Read code excerpt

        self.register_buffer("kv_cache", torch.zeros(args.max_batch_size, args.max_seq_len, self.kv_lora_rank), persistent=False)
        self.register_buffer("pe_cache", torch.zeros(args.max_batch_size, args.max_seq_len, self.qk_rope_head_dim), persistent=False)

… lines 543–568 omitted …

        # we use fp8 kv cache in actual deployment, so here we simulate the precision by casting kv to fp8 and then back to bf16.
        kv_fp8, kv_scale = act_quant(kv, block_size, self.scale_fmt)
        kv = (kv_fp8.view(-1, block_size).float() * kv_scale.view(-1, 1)).to(kv.dtype).view_as(kv)
        self.kv_cache[:bsz, start_pos:end_pos] = kv
        self.pe_cache[:bsz, start_pos:end_pos] = k_pe.squeeze(2)

Contextual evidence from KV cache

When decoding one token, the implementation absorbs the key–value up-projection into queries and outputs and attends over the cached latent directly.

mla-decode · deepseek-ai/DeepSeek-V3.2-Exp / inference/model.py
Pinned revision 87e509a2e5a1 ↗ · lines 590–606

Read code excerpt

        else:                   # MQA decode
            if self.dequant_wkv_b is None and self.wkv_b.scale is not None:
                self.dequant_wkv_b = weight_dequant(self.wkv_b.weight, self.wkv_b.scale)
            wkv_b = self.wkv_b.weight if self.dequant_wkv_b is None else self.dequant_wkv_b
            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])
            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

            # indexer
            topk_indices = self.indexer(x, qr, start_pos, freqs_cis, mask)
            index_mask = torch.full((bsz, 1, end_pos), float("-inf"), device=x.device).scatter_(-1, topk_indices, 0)
            scores += index_mask.unsqueeze(2)

            scores = scores.softmax(dim=-1)
            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:])

Contextual evidence from KV cache

Reference defaults the configuration does not override: maximum sequence length, YaRN RoPE settings and the softmax scale correction.

model-args · deepseek-ai/DeepSeek-V3.2-Exp / inference/model.py
Pinned revision 87e509a2e5a1 ↗ · lines 56–86

Read code excerpt

    max_seq_len: int = 4096 * 4

… lines 57–80 omitted …

    original_seq_len: int = 4096
    rope_theta: float = 10000.0
    rope_factor: float = 40
    beta_fast: int = 32
    beta_slow: int = 1
    mscale: float = 1.

Contextual evidence from Mix and project

Head outputs are flattened and projected back to the model width.

mla-output · deepseek-ai/DeepSeek-V3.2-Exp / inference/model.py
Pinned revision 87e509a2e5a1 ↗ · lines 607–608

Read code excerpt

        x = self.wo(x.flatten(2))
        return x