Closed rbrugaro closed 3 months ago
The leaked semaphore issue is observed when we use all three types of devices -- CPU, CUDA, or HPU. CUDA: CPU:
I placed a breakpoint after model.stop_multi_process_pool(pool) and observed that the 'leaked semaphore' warning occurs only after the breakpoint, while the python file is being closed. Therefore, this seems beyond the scope of sentence_transformers.
HPU
Collaborated debug efforts from @ZhengHongming888 and @rbrugaro
Thanks, Poovaiah
Thanks!
Code to reproduce error:
Output when running multiprocess one card
result is correct but there is leaked semaphone and when running on multiple cards, card utilization seems wrong and even higher number of leaked semaphores.