Personal blog and technical writing by Yashwanthhttps://yashwk.me/https://yashwk.me/blog/running-35b-moe-on-8gb-vram-mosaic/https://yashwk.me/blog/running-35b-moe-on-8gb-vram-mosaic/Treating LLM inference as a systems memory hierarchy problem: tiered mmap streaming, C++ AVX2 SIMD kernels, GPU LRU caching, and hybrid attention.Mon, 05 Oct 2026 00:00:00 GMThttps://yashwk.me/blog/aerospace-simulation-architecture-strikeengine/https://yashwk.me/blog/aerospace-simulation-architecture-strikeengine/Designing a high-throughput C++23 flight simulation and GNC engine using Structure-of-Arrays memory, 1 ms physical truth, and Vulkan GPU compute acceleration.Thu, 10 Sep 2026 00:00:00 GMThttps://yashwk.me/blog/physical-optics-radar-cross-section/https://yashwk.me/blog/physical-optics-radar-cross-section/How StrikeCEM generates monostatic radar cross-section databases from 3D surface meshes using Physical Optics, PTD fringe correction, and CUDA acceleration.Sat, 15 Aug 2026 00:00:00 GMThttps://yashwk.me/blog/terrain-compression-in-libxtm/https://yashwk.me/blog/terrain-compression-in-libxtm/Designing the .xtm geospatial format: combining rate-distortion quadtree partitioning, 6 deterministic predictors, and sub-millisecond Region-of-Interest decoding in C++20.Mon, 20 Jul 2026 00:00:00 GMT