<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/decoder-architecture</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/the-decoder-only-design</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/understanding-autoregressive-generation</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/the-causal-masking-requirement</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/anatomy-of-a-decoder-block</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/gpt-style-decoder-architecture</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/layer-stacking-and-information-flow</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/visualizing-causal-attention-patterns</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/the-generation-loop</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/key-value-caching-for-efficient-generation</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/decoder-architecture-comparison</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/when-to-use-decoder-only-models</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/limitations-and-impact</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/key-parameters</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/summary</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/decoder-architecture-causal-masking-autoregressive-transformers/quiz</loc><lastmod>2025-06-19T00:00:00.000Z</lastmod></url></urlset>