claire_1124
claire_1124
MModular
Created by claire_1124 on 4/12/2024 in #questions
Max Engine: Benchmark my model
When max engine is applied to my model, the result is "50 percetile latency (ns): 3410544, Mean latency (ns):3414190". I tried changing the options (ex: --mlperf-scenario ), but it did not show better performance. Is there any way to tune it? Thanks 🙂
1 replies