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
A CPU memory leak is observed when inferencing using GPU, even when NativeOps is not used (by removing libllm_sharp_ops.so).
CPU memory continues to grow while inferencing. Diagnostics from torch.Tensor.TotalCount and torch.Tensor.PeakCount is stable during multiple turns of chat. GPU memory is also stable, and no GPU memory leak is observed.
Profiled the program with valgrind massif and memcheck. No obvious clues for the leakage from the logs.
A CPU memory leak is observed when inferencing using GPU, even when
NativeOps
is not used (by removing libllm_sharp_ops.so).CPU memory continues to grow while inferencing. Diagnostics from
torch.Tensor.TotalCount
andtorch.Tensor.PeakCount
is stable during multiple turns of chat. GPU memory is also stable, and no GPU memory leak is observed.Profiled the program with valgrind massif and memcheck. No obvious clues for the leakage from the logs.
massif.out.gz
vgdump.gz
The text was updated successfully, but these errors were encountered: