July 7, 2026 Training Compute-Optimal Large Language Models (Chinchilla) Chinchilla论文提出计算最优的LLM缩放定律：模型大小和训练token数应按同等比例缩放（各为C^0.5），发现当前LLM严重欠训练，Chinchilla(70B/1.4T)在相同计算量下显著超越Gopher(280B)/GPT-3(175B)。 large-language-model model-scaling training-optimization scaling-laws
June 8, 2026 Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism 使用模型并行训练数十亿参数语言模型 efficient-attention distributed-training large-language-model llm-training parallelism-dp llm-inference