You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is there a known memory leak in cmem?
I found this in the logs from valgrind.
==1049== HEAP SUMMARY:
==1049== in use at exit: 1,349,153,600 bytes in 1,333,650 blocks
==1049== total heap usage: 2,621,433 allocs, 1,287,783 frees, 2,955,906,430 bytes allocated
==1049==
==1049== 32 bytes in 1 blocks are definitely lost in loss record 85,881 of 182,145
==1049== at 0x4C3017F: operator new(unsigned long) (in /usr/lib/valgrind/vgpreload_memcheck-amd64-linux.so)
==1049== by 0x5C56659: cnmem::Manager::allocateBlockUnsafe(cnmem::Block*&, cnmem::Block*&, unsigned long) (in /opt/tritonserver/lib/libtritonserver.so)
==1049== by 0x5C57568: cnmem::Manager::reserve(unsigned long)
==1049== by 0x5C5806B: cnmemInit
The text was updated successfully, but these errors were encountered:
Is there a known memory leak in cmem?
I found this in the logs from valgrind.
The text was updated successfully, but these errors were encountered: