https://umang-projects.github.io/posts/flashMLA/ 2026-02-15T16:14:33+00:00 https://umang-projects.github.io/posts/matmul_V1/ 2025-02-15T00:00:00+00:00 https://umang-projects.github.io/posts/matmul_V2/ 2025-02-15T00:00:00+00:00 https://umang-projects.github.io/posts/matmul_V1/ 2025-02-15T00:00:00+00:00 https://umang-projects.github.io/posts/fourth/ 2025-08-05T12:37:32+00:00 https://umang-projects.github.io/posts/first/ 2025-07-29T08:03:24+00:00 https://umang-projects.github.io/posts/second/ 2025-07-29T08:03:24+00:00 https://umang-projects.github.io/posts/third/ 2025-08-05T11:58:57+00:00 https://umang-projects.github.io/posts/CUDA_Divergence/ 2025-08-14T09:47:30+00:00 https://umang-projects.github.io/posts/Cuda-Image/ 2025-10-23T01:45:32+00:00 https://umang-projects.github.io/categories/ 2026-02-17T20:38:20+00:00 https://umang-projects.github.io/tags/ 2026-02-17T20:38:20+00:00 https://umang-projects.github.io/archives/ 2026-02-17T20:38:20+00:00 https://umang-projects.github.io/about/ 2026-02-17T20:38:20+00:00 https://umang-projects.github.io/ https://umang-projects.github.io/tags/triton/ https://umang-projects.github.io/tags/cuda/ https://umang-projects.github.io/tags/gpu-kernels/ https://umang-projects.github.io/tags/memory-optimization/ https://umang-projects.github.io/tags/deep-learning/ https://umang-projects.github.io/tags/learning-journey/ https://umang-projects.github.io/tags/fine-tuning/ https://umang-projects.github.io/tags/qlora/ https://umang-projects.github.io/tags/llm/ https://umang-projects.github.io/tags/mistral/ https://umang-projects.github.io/tags/phi-4/ https://umang-projects.github.io/tags/structured-data-extraction/ https://umang-projects.github.io/tags/json/ https://umang-projects.github.io/tags/nlp/ https://umang-projects.github.io/tags/transformers/ https://umang-projects.github.io/tags/peft/ https://umang-projects.github.io/tags/optimization/ https://umang-projects.github.io/tags/gpu/ https://umang-projects.github.io/tags/tiling/ https://umang-projects.github.io/tags/performance/ https://umang-projects.github.io/tags/matrix-multiplication/ https://umang-projects.github.io/tags/hylora/ https://umang-projects.github.io/tags/svd/ https://umang-projects.github.io/tags/lora/ https://umang-projects.github.io/tags/llama/ https://umang-projects.github.io/tags/perplexity/ https://umang-projects.github.io/tags/performance-trade-off/ https://umang-projects.github.io/tags/fine-tuning/ https://umang-projects.github.io/tags/profiling/ https://umang-projects.github.io/tags/bottleneck/ https://umang-projects.github.io/tags/attention/ https://umang-projects.github.io/tags/transformer/ https://umang-projects.github.io/tags/shared-memory/ https://umang-projects.github.io/tags/cuda/ https://umang-projects.github.io/tags/warp-divergence/ https://umang-projects.github.io/tags/parallel-computing/ https://umang-projects.github.io/tags/shared-memory/ https://umang-projects.github.io/tags/matrix-multiplication/ https://umang-projects.github.io/categories/gpu-optimization/ https://umang-projects.github.io/categories/deep-learning/ https://umang-projects.github.io/categories/systems-programming/ https://umang-projects.github.io/categories/nlp/ https://umang-projects.github.io/categories/llm-fine-tuning/ https://umang-projects.github.io/categories/cuda/ https://umang-projects.github.io/categories/model-compression/ https://umang-projects.github.io/categories/low-rank-adaptation/ https://umang-projects.github.io/categories/parallel-computing/ https://umang-projects.github.io/categories/maths/ https://umang-projects.github.io/categories/parallel-computing/ https://umang-projects.github.io/categories/image/