Skip to content

GitLab

Commit 554296b4 authored by wenjh's avatar wenjh
Browse files

Merge branch 'develop_v2.5'

parents dcb27bde 1f97aebb
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
transformer_engine/common/gemm/rocm_gemm.cu
View file @ 554296b4
...@@ -1610,10 +1610,10 @@ void hipblaslt_goupedgemm(std::vector<const Tensor*>& inputA, std::vector<const ...@@ -1610,10 +1610,10 @@ void hipblaslt_goupedgemm(std::vector<const Tensor*>& inputA, std::vector<const
// Copy them to device memory // Copy them to device memory
// 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, NVTE_CHECK_CUDA(hipMemcpy(d_userArgs,
userArgs, userArgs,
m.size() * sizeof(hipblaslt_ext::UserArguments), m.size() * sizeof(hipblaslt_ext::UserArguments),
hipMemcpyHostToDevice, stream)); hipMemcpyHostToDevice));
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));
// NVTE_CHECK_HIPBLASLT(groupedgemm.run(stream)); // NVTE_CHECK_HIPBLASLT(groupedgemm.run(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