Projects

Projects

Apple Silicon inference engines, an online judge for the CPE, and tools that automate something tedious. Filter by topic or search the stack.

7 projects

Fork of Inco's Splash 246 Metal · C++ · Apple7/8 GPUs

Splash for M1 and M2

Splash is Inco's local inference engine for Qwen3.8-27B, and this is my port for M1 and M2. Its kernels used bfloat16 and Apple's MPP matrix library, which those GPUs do not run well; I rewrote them to use formats the M1 runs natively.

  • simdgroup_matrix
  • Metal
  • speculative decoding
  • GGUF / MLX 4-bit
Installer 34 LM Studio · llama.cpp

LM Studio + Ternary Bonsai 2

Makes LM Studio load Ternary Bonsai 2 GGUF models (PQ2_0 and PTQ1_0) through Prism's llama.cpp fork, with a reasoning-effort selector. Linux and Windows, double-click install.

  • LM Studio
  • llama.cpp
  • GGUF
Patch + guide 8 oMLX · mlx-vlm

oMLX + Prism Hadamard packs

Makes oMLX load Prism Hadamard Qwen3.5 packs (Ternary Bonsai 2), plus a guide to adding an unrecognised architecture to mlx-vlm.

  • oMLX
  • mlx-vlm
  • Hadamard
Desktop app PyQt6 · Python

Chat Data Exporter

PyQt6 desktop app that extracts WhatsApp and Telegram contacts from thousands of websites.

  • PyQt6
  • Python
  • scraping
Plugin PHP · Moodle

Moodle PWA plugin

Makes a Moodle site installable as a PWA from Chrome, using the site's own logo.

  • Moodle
  • PWA
  • PHP
Contribution FastAPI · Celery · Docker sandbox

YZU Judge

An online judge for the CPE, the programming exam many Taiwanese universities require for graduation, made for Yuan Ze University: 299 problems from real past exams, code judged in sandboxed containers and timed mock exams. Akmal Agzamov and I build and run it together.

  • online judge
  • FastAPI
  • Docker
  • i18n