Skip to content

vllm.models.kimi_k3.nvidia.specialized_decode.cutedsl.gemm

Modules:

  • projection –

    Split-K projection on the FlashInfer CuTe core vendored in splitk.py (with an

  • splitk –

    FlashInfer 0.7.0.post1 SplitKDenseGemmKernel (dense_bf16_gemm_sm100_splitk)

  • ws_gemm –

    Weight-stationary skinny GEMM for the MoE front: y[M, N] = x[M, K] @ W[N, K]^T.