https://pycheng.github.io/Write-ishpyc blog 2026-04-30T13:30:16+00:00 pyc https://pycheng.github.io/ Jekyll © 2026 pyc /assets/img/favicons/favicon.ico /assets/img/favicons/favicon-96x96.png [2hr route]Taipei Riverside Bikeway2026-04-26T00:00:28+00:00 2026-04-30T13:29:20+00:00 https://pycheng.github.io/posts/2hr.route-Taipei-Riverside-Bikeway/ pyc This is a flat bicycle path connecting the area near New Taipei/Banqiao Station to Taipei/SongShan Train Station. Travelers can easily rent a bicycle from near Banqiao Station, and after 10-15 minutes of riding on city streets, reach the riverside bike path. Following a two-hour ride passing various riverside attractions along the right bank of the Tamsui River and the left bank of the Keelung ... Misc Cycling Plan2026-04-04T00:00:28+00:00 2026-04-04T00:00:28+00:00 https://pycheng.github.io/posts/Plan-C/ pyc Route BQ - 大溪 Accesory 卡踏功率計 Garmin Rally Magene P715 Shimano / Look Estimating VRAM Requirements for GGUF Models2026-03-23T12:00:28+00:00 2026-03-24T08:53:20+00:00 https://pycheng.github.io/posts/LLM-VRAM/ pyc When deploying LLMs locally using llama.cpp, the most common question is: “Will this fit on my GPU?” To calculate the VRAM required for a GGUF model, you must account for three main components: the Weights (the model itself), the KV Cache (context memory), and the Activation/Overhead (the GPU’s workspace). The general formula is: \(VRAM \approx \text{Model Weight Size} + \text{KV Cache Size} + ... llama.cpp Windows Setup2026-03-22T12:00:28+00:00 2026-03-22T14:28:33+00:00 https://pycheng.github.io/posts/llama.cpp/ pyc Windows Setup Experience for llama.cpp This documentation details the process of installing llama.cpp on a Windows environment, operating the llama-cli, and utilizing the llama-bench for performance assessment. The text covers pre-requisites, installation steps and examples of command-line interaction with models. It also covers methods for using the benchmarking tool to evaluate system speed ... Hello World2026-03-22T08:46:28+00:00 2026-03-22T11:05:22+00:00 https://pycheng.github.io/posts/hello-world/ pyc Hello World In memory of M, who started it all, and in celebration of J, who continues the journey by my side. Blog Setup & Workflow Writing a new post Enable Comments Favicon