Module kimi_k3 

Kimi K3 host graph. This slice is KDA only.

K3-DECISION: KDA is a new backend. Do not copy GDN / Mamba-2 / Qwen3-Next / glm5next_kda kernels into kernels/gb10/kimi-k3/. CUDA: kda_decode.cu (default; K3_CUDA_KDA=0 CPU escape).

Re-exports

pub use attnres::AttnResHub;

pub use attnres::attnres_blend;

pub use attnres::attnres_mix;

pub use attnres::attnres_softmax_mix;

pub use cache::HybridCache;

pub use cache::LayerCache;

pub use cache::MlaKv;

pub use expert_backend::ExpertBackendKind;

pub use expert_backend::MmapExpertStore;

pub use expert_backend::PrefetchPlanner;

pub use expert_backend::kind_from_env;

pub use kda::KDA_L2_EPS;

pub use kda::KdaConfig;

pub use kda::KdaState;

pub use kda::cuda_kda_enabled;

pub use kda::kda_decode_token;

pub use kda::kda_from;

pub use latent_moe::LatentMoeConfig;

pub use latent_moe::latent_moe_forward;

pub use latent_moe::mix_routed_experts;

pub use latent_moe::moe_from;

pub use latent_moe::sigmoid_topk;

pub use layer::K3Graph;

pub use layer::K3LayerSpec;

pub use layer::MixerKind;

pub use layer::MlpKind;

pub use mla::MlaConfig;

pub use mla::cuda_mla_enabled;

pub use mla::gated_mla_attend;

pub use mla::mla_decode_token;

pub use mla::mla_from;

pub use situ::situ_glu;

pub use situ::situ_glu_vec;

pub use situ::softcap;

Modules

attnres

Block AttnRes CPU reference.

cache

Hybrid cache: paged MLA KV + KDA recurrent/conv state.

expert_backend

Expert storage backend for K3 routed MXFP4 packs.

kda

Kimi K3 KDA CPU reference — a new backend, not GDN / Mamba-2.

latent_moe

Stable LatentMoE CPU reference.

layer

One K3 decoder layer as host graph data: mixer + MLP + AttnRes sites.

mla

Gated NoPE MLA CPU reference.

situ

SiTU-GLU CPU reference.