v4.0 update. (#2371)

This commit is contained in:
Junkai-Wu
2025-06-06 02:39:20 -04:00
committed by GitHub
parent 2e2af190bd
commit 8bdbfca682
254 changed files with 29751 additions and 1980 deletions
@@ -749,7 +749,7 @@ Status BlockwiseGemmOperationProfiler::initialize_workspace(
gemm_workspace_.arguments.use_pdl = problem_.use_pdl;
/* Query device SM count to pass onto the kernel as an argument, where needed */
gemm_workspace_.arguments.sm_count = options.device.properties[0].multiProcessorCount;
gemm_workspace_.arguments.sm_count = options.device.get_sm_count(0);
}
//