Alex(@Alex_tra_memory):Thanks for the model, we were able to port Laya to coreml with 99.5% of the ops on ANE + benchmarked too. it is now blazing fast with 3.7 ms per decision on an M5 Pro. Release: https://t.co/9xerYIHt9y Models: https://t.co/kPOaMQI4RH

Alex

@Alex_tra_memory

@fluidinference , AI Researcher

加入 July 2025

121 正在關注 690 粉絲

Alex@Alex_tra_memory

2026.09.21 22:20

Thanks for the model, we were able to port Laya to coreml with 99.5% of the ops on ANE + benchmarked too. it is now blazing fast with 3.7 ms per decision on an M5 Pro. Release: Models:

854

轉發到社區

熱門用戶

2M 粉絲

260.1K 粉絲

101.7K 粉絲

578.9K 粉絲

40.1K 粉絲

4.3M 粉絲

28.3K 粉絲

26.4M 粉絲

182.9K 粉絲

549.7K 粉絲

140.1K 粉絲

3.4M 粉絲

111K 粉絲

0 粉絲

2.1M 粉絲