Delete sgl-kernel AOT router GEMM and fused A GEMM (#30280)

Co-authored-by: Brayden Zhong <brayden@radixark.ai> Co-authored-by: root <root@sgl-b300-inference.datacrunch.io>
2026-07-22 08:44:59 +08:00
parent 8ae0eb83fc
commit 03342e7732
19 changed files with 10 additions and 1834 deletions
@@ -256,7 +256,6 @@ void sgl_per_token_group_quant_8bit_v2(
    bool fuse_silu_and_mul,
    const std::optional<torch::Tensor>& masked_m);
 void sgl_per_token_quant_fp8(at::Tensor input, at::Tensor output_q, at::Tensor output_s);
-void dsv3_fused_a_gemm(torch::Tensor& output, torch::Tensor const& mat_a, torch::Tensor const& mat_b);

 torch::Tensor gptq_gemm(
    torch::Tensor a,