leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 27 Packages Projects Releases Wiki Activity

v4.4 update. (#2979)

Browse Source
This commit is contained in:
Junkai-Wu
2026-01-24 11:46:17 -05:00
committed by GitHub
parent 2fafefb7b9
commit 9fba3195f9
293 changed files with 46343 additions and 2995 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/profiler/include/cutlass/profiler/grouped_gemm_operation_profiler.h
+24 -2
View File
@@ -318,8 +318,30 @@ protected:
int swizzle_size,
bool is_dynamic_cluster_enabled);
/// Verifies CUTLASS against host and device references
bool verify_with_reference_(
/// Verifies CUTLASS against device reference (for regular grouped GEMM)
bool verify_with_device_reference_(
Options const& options,
PerformanceReport& report,
DeviceContext& device_context,
library::Operation const* operation,
ProblemSpace const& problem_space,
ProblemSpace::Problem const& problem,
cutlass::library::NumericTypeID element_A,
cutlass::library::NumericTypeID element_B);
/// Verifies CUTLASS against host reference (for regular grouped GEMM)
bool verify_regular_with_host_reference_(
Options const& options,
PerformanceReport& report,
DeviceContext& device_context,
library::Operation const* operation,
ProblemSpace const& problem_space,
ProblemSpace::Problem const& problem,
cutlass::library::NumericTypeID element_A,
cutlass::library::NumericTypeID element_B);
/// Verifies CUTLASS against host reference (for block-scaled/blockwise grouped GEMM)
bool verify_block_with_host_reference_(
Options const& options,
PerformanceReport& report,
DeviceContext& device_context,