Skip to content

GitLab

Commit 623ae795 authored by wenjh's avatar wenjh
Browse files

fix build error 


Signed-off-by: wenjh's avatarwenjh <wenjh@sugon.com>
parent b3833972
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
transformer_engine/common/gemm/rocm_gemm.cu
View file @ 623ae795
...@@ -1350,7 +1350,7 @@ void hipblaslt_goupedgemm(std::vector<const Tensor*>& inputA, std::vector<const ...@@ -1350,7 +1350,7 @@ void hipblaslt_goupedgemm(std::vector<const Tensor*>& inputA, std::vector<const
hipblaslt_ext::UserArguments* d_userArgs; hipblaslt_ext::UserArguments* d_userArgs;
NVTE_CHECK_CUDA(hipMallocAsync(&d_userArgs, m.size() * sizeof(hipblaslt_ext::UserArguments), stream)); NVTE_CHECK_CUDA(hipMallocAsync(&d_userArgs, m.size() * sizeof(hipblaslt_ext::UserArguments), stream));
NVTE_CHECK_CUDA(hipMemcpyAsync(d_userArgs, userArgs, m.size() * sizeof(hipblaslt_ext::UserArguments), NVTE_CHECK_CUDA(hipMemcpyAsync(d_userArgs, userArgs, m.size() * sizeof(hipblaslt_ext::UserArguments),
hipMemcpyHostToDevice), stream); hipMemcpyHostToDevice, stream));
NVTE_CHECK_HIPBLASLT(groupedgemm.run(d_userArgs, stream)); NVTE_CHECK_HIPBLASLT(groupedgemm.run(d_userArgs, stream));
// NVTE_CHECK_HIPBLASLT(groupedgemm.initialize(heuristicResult[0].algo, workspace, false, stream)); // NVTE_CHECK_HIPBLASLT(groupedgemm.initialize(heuristicResult[0].algo, workspace, false, stream));
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment