https://longformexplainers.com/https://longformexplainers.com/account/https://longformexplainers.com/glossary/https://longformexplainers.com/llm-inference/https://longformexplainers.com/llm-inference/01-what-is-an-llm/https://longformexplainers.com/llm-inference/02-tokens/https://longformexplainers.com/llm-inference/03-embeddings/https://longformexplainers.com/llm-inference/04-attention/https://longformexplainers.com/llm-inference/05-multi-head/https://longformexplainers.com/llm-inference/06-positional-encoding/https://longformexplainers.com/llm-inference/07-mlp/https://longformexplainers.com/llm-inference/08-transformer-block/https://longformexplainers.com/llm-inference/09-full-model/https://longformexplainers.com/llm-inference/10-sampling/https://longformexplainers.com/llm-inference/11-prefill-decode/https://longformexplainers.com/llm-inference/12-kv-cache/https://longformexplainers.com/llm-inference/13-memory-hierarchy/https://longformexplainers.com/llm-inference/14-continuous-batching/https://longformexplainers.com/llm-inference/15-paged-attention/https://longformexplainers.com/llm-inference/16-prefix-caching/https://longformexplainers.com/llm-inference/17-chunked-prefill/https://longformexplainers.com/llm-inference/18-speculative-decoding/https://longformexplainers.com/llm-inference/19-parallelism/https://longformexplainers.com/llm-inference/20-throughput-vs-latency/https://longformexplainers.com/llm-inference/21-recap/https://longformexplainers.com/llm-post-training/https://longformexplainers.com/llm-post-training/01-what-is-post-training/https://longformexplainers.com/llm-post-training/02-probability-and-policies/https://longformexplainers.com/llm-post-training/03-from-next-token-to-behavior/https://longformexplainers.com/llm-post-training/04-the-alignment-problem/https://longformexplainers.com/llm-post-training/05-instruction-tuning/https://longformexplainers.com/llm-post-training/06-sft-in-practice/https://longformexplainers.com/llm-post-training/07-synthetic-and-self-generated/https://longformexplainers.com/llm-post-training/08-learning-from-preferences/https://longformexplainers.com/llm-post-training/09-optimizing-against-the-reward/https://longformexplainers.com/llm-post-training/10-rlhf-scales-to-language/https://longformexplainers.com/llm-post-training/11-reward-models/https://longformexplainers.com/llm-post-training/12-rlaif-constitutional/https://longformexplainers.com/llm-post-training/13-policy-gradients-reinforce/https://longformexplainers.com/llm-post-training/14-value-advantage-baselines/https://longformexplainers.com/llm-post-training/15-trpo-to-ppo/https://longformexplainers.com/llm-post-training/16-ppo-for-rlhf/https://longformexplainers.com/llm-post-training/17-reward-hacking/https://longformexplainers.com/llm-post-training/18-dpo/https://longformexplainers.com/llm-post-training/19-the-dpo-zoo/https://longformexplainers.com/llm-post-training/20-rejection-sampling-alignment/https://longformexplainers.com/llm-post-training/21-bootstrapping-reasoning/https://longformexplainers.com/llm-post-training/22-process-vs-outcome-rewards/https://longformexplainers.com/llm-post-training/23-inference-scaling-o1/https://longformexplainers.com/llm-post-training/24-rl-from-verifiable-rewards/https://longformexplainers.com/llm-post-training/25-grpo-and-deepseek-r1/https://longformexplainers.com/llm-post-training/26-grpo-refinements/https://longformexplainers.com/llm-post-training/27-scaling-open-post-training/https://longformexplainers.com/llm-post-training/28-agentic-and-tool-use-rl/https://longformexplainers.com/llm-post-training/29-on-policy-distillation/https://longformexplainers.com/llm-post-training/30-rl-scaling-laws/https://longformexplainers.com/llm-post-training/31-generative-reward-models/https://longformexplainers.com/llm-post-training/32-recap/https://longformexplainers.com/llm-pretraining/https://longformexplainers.com/llm-pretraining/01-what-is-pretraining/https://longformexplainers.com/llm-pretraining/02-next-token-objective/https://longformexplainers.com/llm-pretraining/03-gradient-descent-backprop/https://longformexplainers.com/llm-pretraining/04-optimizers-and-schedules/https://longformexplainers.com/llm-pretraining/05-precision-and-numerics/https://longformexplainers.com/llm-pretraining/06-compute-and-memory/https://longformexplainers.com/llm-pretraining/07-parallelism/https://longformexplainers.com/llm-pretraining/08-data-pipeline/https://longformexplainers.com/llm-pretraining/09-attention-transformer/https://longformexplainers.com/llm-pretraining/10-gpt1-generative-pretraining/https://longformexplainers.com/llm-pretraining/11-bert-masked-lm/https://longformexplainers.com/llm-pretraining/12-gpt2-scale-zeroshot/https://longformexplainers.com/llm-pretraining/13-t5-text-to-text/https://longformexplainers.com/llm-pretraining/14-scaling-laws-kaplan/https://longformexplainers.com/llm-pretraining/15-gpt3-few-shot/https://longformexplainers.com/llm-pretraining/16-chinchilla-compute-optimal/https://longformexplainers.com/llm-pretraining/17-llama3/https://longformexplainers.com/llm-pretraining/18-deepseek-v3/https://longformexplainers.com/llm-pretraining/19-qwen25/https://longformexplainers.com/llm-pretraining/20-gemma2/https://longformexplainers.com/llm-pretraining/21-synthetic-data/https://longformexplainers.com/llm-pretraining/22-gemma3/https://longformexplainers.com/llm-pretraining/23-training-methods-survey/https://longformexplainers.com/llm-pretraining/24-kimi-k2-5/https://longformexplainers.com/llm-pretraining/25-qwen3-coder-next/https://longformexplainers.com/llm-pretraining/26-deepseek-v4/https://longformexplainers.com/llm-pretraining/27-qwen35-omni/https://longformexplainers.com/llm-pretraining/28-recap/https://longformexplainers.com/login/https://longformexplainers.com/signup/