We test normal kernels on A3 384 SuperPOD. And we follow the DeepSeek-V3/R1 pretraining setting (4096 tokens per batch, 7168 hidden, top-8 experts, INT8 dispatching and BF16 combining).
Abstract: Traditional optimization-based techniques for time-synchronized state estimation (SE) often suffer from high online computational burden, limited phasor measurement unit (PMU) coverage, and ...
Abstract: In dual-functional radar-communication (DFRC) systems, to achieve desirable performance in both direction-of-arrival (DoA) estimation for sensing targets and wireless communication for user ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback