fix: ZLUDA compatibility issues (#582)

feat: koharu-ai crate

refactor: move keyring to koharu-runtime

feat: add AMD GPU support via ZLUDA (#362)

fix: http timeouts

feat: pluggable engine system with DAG pipeline

refactor: simplify Tauri setup and dev server

refactor: rewrite backend storage, config, and runtime

feat: bootstrap window

refactor: merge crates

fix(linux): load native libraryes by using explicit path to resolve missing libggml errors on Unix systems (#295)

feat: llama.cpp-based paddleocr-vl-1.5

refactor: koharu-runtime

chore: remove unused fonts

chore: add more context info

chore: reorganize code

feat: google fonts

refactor: re-introduce koharu-core

fix: pypi mirror

refactor: use koharu-ml

refactor: reorganize module imports and update dylib function calls

perf: download with http range

refactor: use stream for http request

feat: add tracing events for download events

refactor: reorganize dylib handling and update HTTP client references

feat: Implement core application structure and functionality

Add koharu-models crate with implementations for comic text detection, image inpainting, LLM generation, and manga OCR

Refactor koharu and koharu-runtime: