Add dsv3 fused a gemm to sgl-kernel (#7630)

2025-06-29 17:52:24 +08:00
parent 071a1f51ae
commit 04b35190e2
9 changed files with 800 additions and 0 deletions
--- a/sgl-kernel/include/sgl_kernel_ops.h
+++ b/sgl-kernel/include/sgl_kernel_ops.h
@@ -201,6 +201,8 @@ void bmm_fp8(
    int64_t cublas_handle,
    int64_t cuda_stream);

+void dsv3_fused_a_gemm(torch::Tensor& output, torch::Tensor const& mat_a, torch::Tensor const& mat_b);
+
 /*
 * From csrc/moe
 */