https://kapilsh.github.io/posts/geometry-of-regression/ 2024-07-11T15:42:06-04:00 https://kapilsh.github.io/posts/gram-schmidt-procedure/ 2024-07-11T15:42:06-04:00 https://kapilsh.github.io/posts/how-to-zmq-proxy/ 2024-07-11T15:42:06-04:00 https://kapilsh.github.io/posts/kernel-smoothing/ 2024-07-11T15:42:06-04:00 https://kapilsh.github.io/posts/local-linear-regression/ 2024-07-11T15:42:06-04:00 https://kapilsh.github.io/posts/regularization-in-linear-models/ 2024-07-11T15:42:06-04:00 https://kapilsh.github.io/posts/my-personal-setup/ 2024-07-11T15:42:06-04:00 https://kapilsh.github.io/posts/playing-with-opencv/ 2019-02-16T00:00:00-05:00 https://kapilsh.github.io/posts/dog-detection/ 2019-02-19T00:00:00-05:00 https://kapilsh.github.io/posts/dog-breed-classification/ 2019-03-22T00:00:00-04:00 https://kapilsh.github.io/posts/dog-breed-classification-tl/ 2019-04-04T00:00:00-04:00 https://kapilsh.github.io/posts/convolutional-autoencoders/ 2020-09-07T00:00:00-04:00 https://kapilsh.github.io/posts/lstm-writes-animal-farm/ 2021-04-21T00:00:00-04:00 https://kapilsh.github.io/posts/system-design-interview-process/ 2021-09-23T00:00:00-04:00 https://kapilsh.github.io/posts/cuda-mode-fusing-kernels-talk/ 2024-07-26T15:52:26-04:00 https://kapilsh.github.io/posts/transformers-from-scratch/ 2024-07-15T22:32:07-04:00 https://kapilsh.github.io/posts/exploring-gpt2/ 2024-07-31T14:29:45-04:00 https://kapilsh.github.io/posts/logits-to-text/ 2024-07-19T00:00:00-04:00 https://kapilsh.github.io/posts/benchmark-gpt/ 2024-07-31T15:58:41-04:00 https://kapilsh.github.io/posts/deep-dive-into-triton-internals/ 2024-09-15T06:54:58-04:00 https://kapilsh.github.io/posts/deep-dive-into-triton-internals-2/ 2024-09-08T07:47:05-04:00 https://kapilsh.github.io/posts/transformers-for-recsys-1/ 2024-09-03T14:13:32-04:00 https://kapilsh.github.io/posts/transformers-for-recsys-2/ 2024-09-03T00:00:00-04:00 https://kapilsh.github.io/posts/deep-dive-into-triton-internals-3/ 2025-09-14T08:23:23-04:00 https://kapilsh.github.io/posts/gpu-mode-triton-internals-talk/ 2024-09-30T00:00:00-04:00 https://kapilsh.github.io/posts/transformers-for-recsys-3/ 2025-01-03T06:02:32-05:00 https://kapilsh.github.io/posts/ai-gpu-programming-1/ 2025-10-11T06:02:40-04:00 https://kapilsh.github.io/posts/gpt_oss_scratch_inference_hf/ 2025-09-05T10:24:35-04:00 https://kapilsh.github.io/posts/gpt_oss_scratch_reference_implementation/ 2025-09-05T00:00:00-04:00 https://kapilsh.github.io/posts/kv-caching-visualized/ 2025-09-13T00:00:00-04:00 https://kapilsh.github.io/posts/mxfp4-visualizer/ 2025-09-14T22:12:10-04:00 https://kapilsh.github.io/posts/triton-kernels-rms-norm/ 2025-09-18T21:38:06-04:00 https://kapilsh.github.io/posts/triton-kernels-softmax/ 2025-09-24T07:28:40-04:00 https://kapilsh.github.io/posts/triton-kernels-softmax-2/ 2025-09-21T07:59:40-04:00 https://kapilsh.github.io/posts/learn-cutlass-the-hard-way/ 2025-11-09T21:47:26-05:00 https://kapilsh.github.io/posts/learn-cutlass-the-hard-way-2/ 2026-01-01T08:21:17-05:00 https://kapilsh.github.io/posts/nccl-wire-protocols/ 2026-08-16T16:04:48-04:00 https://kapilsh.github.io/categories/ 2026-09-22T05:54:46-04:00 https://kapilsh.github.io/tags/ 2026-09-22T05:54:46-04:00 https://kapilsh.github.io/archives/ 2026-09-22T05:54:46-04:00 https://kapilsh.github.io/mxfp4/ 2026-09-22T05:54:46-04:00 https://kapilsh.github.io/rope/ 2026-09-22T05:54:46-04:00 https://kapilsh.github.io/about/ 2026-09-22T05:54:46-04:00 https://kapilsh.github.io/ https://kapilsh.github.io/tags/python/ https://kapilsh.github.io/tags/machine-learning/ https://kapilsh.github.io/tags/java/ https://kapilsh.github.io/tags/zeromq/ https://kapilsh.github.io/tags/microservices/ https://kapilsh.github.io/tags/kernel-methods/ https://kapilsh.github.io/tags/linux/ https://kapilsh.github.io/tags/general/ https://kapilsh.github.io/tags/deep-learning/ https://kapilsh.github.io/tags/cnn/ https://kapilsh.github.io/tags/ai/ https://kapilsh.github.io/tags/rnn/ https://kapilsh.github.io/tags/interview/ https://kapilsh.github.io/tags/system-design/ https://kapilsh.github.io/tags/recsys/ https://kapilsh.github.io/tags/performance/ https://kapilsh.github.io/tags/pytorch/ https://kapilsh.github.io/tags/transformers/ https://kapilsh.github.io/tags/llm/ https://kapilsh.github.io/tags/triton/ https://kapilsh.github.io/tags/cuda/ https://kapilsh.github.io/tags/compiler/ https://kapilsh.github.io/tags/quantization/ https://kapilsh.github.io/tags/gpu/ https://kapilsh.github.io/tags/kernels/ https://kapilsh.github.io/tags/profiling/ https://kapilsh.github.io/tags/gemm/ https://kapilsh.github.io/tags/nccl/ https://kapilsh.github.io/tags/distributed/ https://kapilsh.github.io/categories/blog/ https://kapilsh.github.io/categories/tutorial/ https://kapilsh.github.io/categories/guide/ https://kapilsh.github.io/categories/talk/ https://kapilsh.github.io/categories/devlog/ https://kapilsh.github.io/categories/tool/ https://kapilsh.github.io/page2/ https://kapilsh.github.io/page3/ https://kapilsh.github.io/page4/ https://kapilsh.github.io/assets/data/nvidia_hopper_presentation.pdf 2026-09-22T05:54:38-04:00 https://kapilsh.github.io/assets/data/triton_internals_presentation.pdf 2026-09-22T05:54:38-04:00