https://mandliya.github.io/blog/2024/LLM_inference_1/ 2025-12-18T06:57:03+00:00 https://mandliya.github.io/blog/2024/LLM_inference_2/ 2025-12-18T06:57:03+00:00 https://mandliya.github.io/blog/2024/scaling_laws/ 2025-12-18T06:57:03+00:00 https://mandliya.github.io/blog/2024/model_architecture_optimizations/ 2025-12-18T06:57:03+00:00 https://mandliya.github.io/blog/2025/from-words-to-meaning-implementing-word2vec-from-scratch/ 2025-12-18T06:57:03+00:00 https://mandliya.github.io/blog/2025/supervised-finetuning-in-llm-training-workflow/ 2025-12-30T07:39:38+00:00 https://mandliya.github.io/blog/2025/visualizing-attention-see-what-an-llm-sees/ 2025-12-30T07:39:38+00:00 https://mandliya.github.io/blog/2025/building-gpt-2-from-scratch-mechanistic-interpretability-view/ 2026-01-12T06:30:11+00:00 https://mandliya.github.io/blog/2025/paper-implementation-steering-language-models-with-activation-engineering/ 2026-01-11T06:55:48+00:00 https://mandliya.github.io/blog/2025/introduction-to-mechanistic-interpretability-superposition-and-sparse-autoencoders/ 2025-12-25T21:32:48+00:00 https://mandliya.github.io/blog/2026/deeply-learning-1-dropout-implementation-from-scratch/ 2026-03-11T19:15:40+00:00 https://mandliya.github.io/blog/2026/deeply-learning-2-cross-entropy-loss-implementation-from-scratch/ 2026-03-11T19:14:53+00:00 https://mandliya.github.io/blog/2026/deeply-learning-3-mean-squared-error-loss-implementation-from-scratch/ 2026-03-04T23:10:09+00:00 https://mandliya.github.io/blog/2026/building-an-autograd-engine-from-scratch-with-cupy-part-1-tensor-and-backpropagation/ 2026-03-14T07:14:09+00:00 https://mandliya.github.io/blog/2026/deeplygrad-part-2-teaching-our-autograd-to-classify-mnist-digits/ 2026-03-14T00:03:39+00:00 https://mandliya.github.io/ https://mandliya.github.io/blog/2024/ https://mandliya.github.io/blog/2025/ https://mandliya.github.io/blog/2026/ https://mandliya.github.io/blog/tag/llm/ https://mandliya.github.io/blog/tag/inference-optimization/ https://mandliya.github.io/blog/tag/transformer/ https://mandliya.github.io/blog/tag/attention-mechanism/ https://mandliya.github.io/blog/tag/multi-head-attention/ https://mandliya.github.io/blog/tag/k-v-caching/ https://mandliya.github.io/blog/tag/memory-calculation/ https://mandliya.github.io/blog/tag/optimization-metrics/ https://mandliya.github.io/blog/tag/optimization-techniques/ https://mandliya.github.io/blog/tag/natural-language-processing/ https://mandliya.github.io/blog/tag/nlp/ https://mandliya.github.io/blog/tag/large-language-models/ https://mandliya.github.io/blog/tag/llms/ https://mandliya.github.io/blog/tag/transformers/ https://mandliya.github.io/blog/tag/ai-accelerators/ https://mandliya.github.io/blog/tag/gpus/ https://mandliya.github.io/blog/tag/tpus/ https://mandliya.github.io/blog/tag/fpgas/ https://mandliya.github.io/blog/tag/asics/ https://mandliya.github.io/blog/tag/parallel-processing/ https://mandliya.github.io/blog/tag/data-parallelism/ https://mandliya.github.io/blog/tag/model-parallelism/ https://mandliya.github.io/blog/tag/task-parallelism/ https://mandliya.github.io/blog/tag/co-processing-mode/ https://mandliya.github.io/blog/tag/intelligent-processing-units/ https://mandliya.github.io/blog/tag/reconfigurable-dataflow-units/ https://mandliya.github.io/blog/tag/neural-processing-units/ https://mandliya.github.io/blog/tag/scaling-laws/ https://mandliya.github.io/blog/tag/emergent-capabilities/ https://mandliya.github.io/blog/tag/mixture-of-experts/ https://mandliya.github.io/blog/tag/group-query-attention/ https://mandliya.github.io/blog/tag/gqa/ https://mandliya.github.io/blog/tag/moe/ https://mandliya.github.io/blog/tag/hardware-acceleration/ https://mandliya.github.io/blog/tag/model-architecture-optimizations/ https://mandliya.github.io/blog/tag/word-embeddings/ https://mandliya.github.io/blog/tag/word2vec/ https://mandliya.github.io/blog/tag/embeddings/ https://mandliya.github.io/blog/tag/embedding-models/ https://mandliya.github.io/blog/tag/deep-learning/ https://mandliya.github.io/blog/tag/neural-networks/ https://mandliya.github.io/blog/tag/supervised-fine-tuning/ https://mandliya.github.io/blog/tag/sft/ https://mandliya.github.io/blog/tag/attention/ https://mandliya.github.io/blog/tag/mechanistic-interpretability/ https://mandliya.github.io/blog/tag/residual-streams/ https://mandliya.github.io/blog/tag/ai-safety/ https://mandliya.github.io/blog/tag/activation-engineering/ https://mandliya.github.io/blog/tag/representation-engineering/ https://mandliya.github.io/blog/tag/alignment/ https://mandliya.github.io/blog/tag/controlibility/ https://mandliya.github.io/blog/tag/repe/ https://mandliya.github.io/blog/tag/superposition/ https://mandliya.github.io/blog/tag/sparse-autoencoders/ https://mandliya.github.io/blog/tag/sae/ https://mandliya.github.io/blog/tag/transformerss/ https://mandliya.github.io/blog/tag/dropout/ https://mandliya.github.io/blog/tag/pytorch/ https://mandliya.github.io/blog/tag/regularization/ https://mandliya.github.io/blog/tag/cross-entropy/ https://mandliya.github.io/blog/tag/loss-functions/ https://mandliya.github.io/blog/tag/mean-squared-error/ https://mandliya.github.io/blog/tag/autograd/ https://mandliya.github.io/blog/tag/backpropagation/ https://mandliya.github.io/blog/tag/cupy/ https://mandliya.github.io/blog/tag/automatic-differentiation/ https://mandliya.github.io/blog/tag/from-scratch/ https://mandliya.github.io/blog/tag/mnist/ https://mandliya.github.io/blog/category/large-language-model/ https://mandliya.github.io/blog/category/inference-optimization/ https://mandliya.github.io/blog/category/natural-language-processing/ https://mandliya.github.io/blog/category/ai-accelerators/ https://mandliya.github.io/blog/category/emegent-capabilities/ https://mandliya.github.io/blog/category/nlp/ https://mandliya.github.io/blog/category/large-language-models/ https://mandliya.github.io/blog/category/llms/ https://mandliya.github.io/blog/category/transformers/ https://mandliya.github.io/blog/category/mechanistic-interpretability/ https://mandliya.github.io/blog/category/ai-safety/ https://mandliya.github.io/blog/category/alignment/ https://mandliya.github.io/blog/category/representation-engineering/ https://mandliya.github.io/blog/category/activation-engineering/ https://mandliya.github.io/blog/category/controlibilitynatural-language-processing/ https://mandliya.github.io/blog/category/superposition/ https://mandliya.github.io/blog/category/sparse-autoencoders/ https://mandliya.github.io/blog/category/sae/ https://mandliya.github.io/blog/category/deeply-learning/ https://mandliya.github.io/blog/category/neural-networks/ https://mandliya.github.io/blog/category/deep-learning/ https://mandliya.github.io/blog/ https://mandliya.github.io/blog/page/2/ https://mandliya.github.io/assets/html/relativity.html 2026-03-14T07:14:24+00:00 https://mandliya.github.io/assets/pdf/example_pdf.pdf 2026-03-14T07:14:25+00:00 https://mandliya.github.io/assets/plotly/demo.html 2026-03-14T07:14:25+00:00 https://mandliya.github.io/assets/rendercv/rendercv_output/Albert_Einstein_CV.pdf 2026-03-14T07:14:25+00:00