Ch-1-LLM-Architecture○Attention Variants○Embeddings○FFNs○GPT Architecture○Normalization○Positional Encodings○TokenizationCh-2-LLM-Training○DPO○Data Pipelines○Distributed Training○Pretraining○RLHFCh-3-LLM-Inference○KV Cache○Quantization○Sampling○Speculative Decoding○vLLM
Ch-1-LLM-Architecture○Attention Variants○Embeddings○FFNs○GPT Architecture○Normalization○Positional Encodings○Tokenization