M
Modular•8mo ago
claire_1124

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 🙂
0 Replies
No replies yetBe the first to reply to this messageJoin
Want results from more Discord servers?
Add your server