![]() * Split apart gemm reference templates into multiple TUs for parallel compilation * remove old files * better balancing of ref kernels across TUs * remove 3 new added refcheck kernels and some un-necessary fp8 library instances to reduce lib size * remove auto fp8 kernels * remove some redundant kernels |
||
---|---|---|
.. | ||
library | ||
profiler | ||
util | ||
CMakeLists.txt |