Kimi K2 · Element-wise product

61 transformer blocks › 60 MoE blocks › Mixture of experts › 384 routed experts

Element-wise product

no parametersself.act_fn(self.gate_proj(x)) * self.up_proj(x)

Gate the up features by the activated gate, feature by feature.

{\htmlData{light=h product}{h}}={\htmlData{light=a silu}{a}}\odot {\htmlData{light=u up}{u}}

in: $a$ [B batch, T positions, 2048 expert d_ff] $u$ [B batch, T positions, 2048 expert d_ff]
out: $h$ [B batch, T positions, 2048 expert d_ff]

Codemodeling_deepseek.py 486–515

modeling_deepseek.py 486–515

        if hasattr(config, "ep_size") and config.ep_size > 1:
            assert config.ep_size == dist.get_world_size()
            self.ep_size = config.ep_size
            self.experts_per_rank = config.n_routed_experts // config.ep_size
            self.ep_rank = dist.get_rank()
            self.experts = nn.ModuleList(
                [
                    (
                        DeepseekV3MLP(
                            config, intermediate_size=config.moe_intermediate_size
                        )
                        if i >= self.ep_rank * self.experts_per_rank
                        and i < (self.ep_rank + 1) * self.experts_per_rank
                        else None
                    )
                    for i in range(config.n_routed_experts)
                ]
            )
        else:
            self.ep_size = 1
            self.experts_per_rank = config.n_routed_experts
            self.ep_rank = 0
            self.experts = nn.ModuleList(
                [
                    DeepseekV3MLP(
                        config, intermediate_size=config.moe_intermediate_size
                    )
                    for i in range(config.n_routed_experts)
                ]
            )

Sources1

Direct evidence

Each routed expert is its own SwiGLU MLP of moe_intermediate_size hidden features.

expert · moonshotai/Kimi-K2-Instruct / modeling_deepseek.py
Pinned revision fd1984e2b7a3 ↗ · lines 486–515

Read code excerpt

        if hasattr(config, "ep_size") and config.ep_size > 1:
            assert config.ep_size == dist.get_world_size()
            self.ep_size = config.ep_size
            self.experts_per_rank = config.n_routed_experts // config.ep_size
            self.ep_rank = dist.get_rank()
            self.experts = nn.ModuleList(
                [
                    (
                        DeepseekV3MLP(
                            config, intermediate_size=config.moe_intermediate_size
                        )
                        if i >= self.ep_rank * self.experts_per_rank
                        and i < (self.ep_rank + 1) * self.experts_per_rank
                        else None
                    )
                    for i in range(config.n_routed_experts)
                ]
            )
        else:
            self.ep_size = 1
            self.experts_per_rank = config.n_routed_experts
            self.ep_rank = 0
            self.experts = nn.ModuleList(
                [
                    DeepseekV3MLP(
                        config, intermediate_size=config.moe_intermediate_size
                    )
                    for i in range(config.n_routed_experts)
                ]
            )