Showing 2026Show all
2 papers · 1 filter
cs.CL2026
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
Dongfang Li, Xiaodong Luo, Ruoyu Sun +62
Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pre…
cs.LG2026
Why Post-Norm Transformers Collapse: Attention Amplification and Gradient Repair Failure
Xingjian Wang, Qingyu Han, Xiaodong Luo +1
Deep decoder-only Transformers often replace the original Post-Norm architecture with Pre-Norm variants because Post-Norm training is highly sensitive to warmup and learning rate u…