torchrec
torchrec copied to clipboard
1.65x qps - remove unnecessary cat
Summary: Research doc: https://docs.google.com/document/d/1nDdQiJDnqJKzjzM3ku__Y5j196uxRVEB00Mj6qAl31k/edit
Run ada model: https://www.internalfb.com/vanguard/serving_test_cases/487129480789691
We can see huge cpu time spend on cat, which is unnecessary for ada cases, we only cat one tensor, should be a no-op. {F1888776749}
Conditionally remove it to improve latency and qps
Reviewed By: 842974287
Differential Revision: D63398565