apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 16:22:57 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Bug fix] fix complie bug when sm < 89 (#2738)

Browse Source
This commit is contained in:
ming1753
2025-07-08 11:24:52 +08:00
committed by GitHub
parent ef6649a577
commit 1eb8ea7328
2 changed files with 44 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
custom_ops/gpu_ops/cpp_extensions.cc
View File

@@ -468,6 +468,7 @@ std::vector<paddle::Tensor> NoauxTc(
int topk,
float routed_scaling_factor);
#ifdef ENABLE_FP8
paddle::Tensor cutlass_fp8_fp8_half_gemm_func(
const paddle::Tensor& x,
const paddle::Tensor& y,
@@ -489,6 +490,7 @@ paddle::Tensor MoeFusedHadamardQuantFp8Func(
paddle::Tensor FusedHadamardQuantFp8Func(
const paddle::Tensor &input,
const float scale);
#endif
PYBIND11_MODULE(fastdeploy_ops, m) {
@@ -769,6 +771,7 @@ PYBIND11_MODULE(fastdeploy_ops, m) {
m.def("noaux_tc",&NoauxTc, "noaux_tc for Deepseekv3 MoE compute");
#ifdef ENABLE_FP8
m.def("cutlass_fp8_fp8_half_gemm_fused", &cutlass_fp8_fp8_half_gemm_func,
py::arg("x"), py::arg("y"), py::arg("bias"), py::arg("transpose_x"),
py::arg("transpose_y"), py::arg("scale"), py::arg("output_dtype"),
@@ -780,4 +783,5 @@ PYBIND11_MODULE(fastdeploy_ops, m) {
m.def("fused_hadamard_quant_fp8", &FusedHadamardQuantFp8Func,
py::arg("input"), py::arg("scale"), "fused_hadamard_quant_fp8 function");
#endif
}