Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00
parent 2e8f54e61e
commit 3de09aadbc
15 changed files with 823 additions and 876 deletions
--- a/sgl-kernel/include/sgl_kernel_ops.h
+++ b/sgl-kernel/include/sgl_kernel_ops.h
@@ -459,7 +459,9 @@ torch::Tensor moe_wna16_marlin_gemm(
    torch::Tensor& a,
    std::optional<torch::Tensor> const& c_or_none,
    torch::Tensor& b_q_weight,
+    std::optional<torch::Tensor> const& b_bias_or_none,
    torch::Tensor& b_scales,
+    std::optional<torch::Tensor> const& global_scale_or_none,
    std::optional<torch::Tensor> const& b_zeros_or_none,
    std::optional<torch::Tensor> const& g_idx_or_none,
    std::optional<torch::Tensor> const& perm_or_none,