TranslatedCovers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning
Repository Index
132,241 visible repositories in the index
1–2 of 2 · Most stars
Hands-on LLM algorithms and systems with PyTorch, Triton & CUDA.《大模型算法与系统教程》:模型架构与训练、后训练、推理加速、性能与算子优化,配套 Notebook 练习、答案解析、测试与实验。