Read-only Gitea pull-mirror of ggml-org/llama.cpp (official upstream). Feeds runtime-deepseek and runtime-glm-generic as the fast local-network fetch source for weekly-sync CI. Do not push here directly.
Updated 2026-08-13 11:07:28 +02:00
GPU-accelerated Whisper transcription API for RTX 2080 (sm_75) — pure Rust, Axum, whisper-rs, CUDA
Updated 2026-08-12 10:51:41 +02:00
Async Instagram Recipe Extractor
Updated 2026-08-11 19:48:54 +02:00
Tonemark — AI-powered audio transcription
Updated 2026-08-06 20:26:38 +02:00
Tuned llama.cpp Docker stack for GTX 1650 Ti — benchmarked KV quant, bigctx, TurboQuant FORCE_MMQ
Updated 2026-07-21 14:08:22 +02:00
Portable cross-runtime code-simplification Agent Skill (ast-grep-driven, two-track apply).
Updated 2026-06-23 03:08:47 +02:00
Updated 2026-06-19 14:54:53 +02:00
Updated 2026-05-25 21:25:24 +02:00
Framework-agnostic async job queue for Node.js
Updated 2026-05-16 18:39:22 +02:00
TrueRef — self-hosted documentation retrieval platform for AI coding assistants
Updated 2026-05-09 15:44:37 +02:00
QuickShell QML greeter for greetd + niri, synced with noctalia-shell theme
Updated 2026-04-30 01:45:42 +02:00
Updated 2026-04-26 12:42:26 +02:00
Legacy TrueRef implementation (superseded by the current Java rewrite)
Updated 2026-04-02 09:50:26 +02:00
Updated 2025-06-06 22:45:05 +02:00
Updated 2024-07-13 19:51:52 +02:00