# Research

Subagent research briefs for the two hosts. Each page is a focused research
findings doc; the project root index () links back.

## LLM Inference

-  The llama.cpp trees on this host compared: positioning, quantization formats, and fit for each machine.
-  Code-level diff of the three llama.cpp trees here: quantization code, type numbers, and what differs for our cards.
-  What SGLang is, how it schedules and caches, how it compares to the runtimes here, and whether it fits this fleet.

## Image / Media

- [[ComfyUI ROCm and Vulkan]] — Whether ComfyUI can use the Strix Halo APU at all, and which backend path actually reaches the GPU.

## Audio / TTS

-  Creating a local voice from sample files: the open-weight cloning landscape, the measured engine A/B, the audio stack.

## Career / Job Search

- [[AI Job Search and Resume Tools]] — Self-hosted job-search and resume tools: the landscape, local-LLM fit, and the recommended homelab stack.

## Self-Hosted Landscape

-  The most-starred self-hosted AI applications of the year so far, with homelab fit and adoption notes.

## Games / Creative

- [[PICO-8 Asset Standards]] — Asset-sheet standards for PICO-8: palette discipline, one light direction, detail hierarchy, cohesion checklist.

## Backups

- [[Backblaze Integration]] — Off-site backup plan for the bind-mounted data on both hosts.

## Legacy

- [[Service Research Brief]] — Consolidated upstream research on the fleet's LLM runtimes, dated to when it was gathered.