GPU Memory 'max_gpu_wrk_mem' seems to be more than the actual GPU type in GPU'20 trace ?

For example in GPU 2020 trace

the job 'e5d6d5b546bff61f93b47ebf' has **max_gpu_wrk_mem** '44.289062' but the gpu type is V100 where the memory capacity should be 16GB or at max 32GB !?

Should I assume that once the **max_gpu_wrk_mem** > **GPU_type_capcity**, the worker encounters OOM ?

Start with the GPU 2020 trace entry for job e5d6d5b546bff61f93b47ebf and compare max_gpu_wrk_mem with the stated V100 capacity. Determine whether the value is a measurement, an aggregate, or an indication of OOM, and document the interpretation of values above the GPU capacity.

Written by the indexing model from the issue text.