Heretek-AI

Mirrored from GitHub organization: Heretek-AI

⚡ Automated nightly builds & portable ROCm 7 releases of Ember for DeepSeek-V4-Flash on AMD Strix Halo (gfx1151 / Radeon 8060S). Standalone C inference server with bundled ROCm runtime, continuous batching, and Homebrew support.
Updated 2026-08-30 18:00:27 -09:00
⚡ Automated nightly builds & portable releases for lucebox (DFlash) inference server on NVIDIA CUDA (sm_75-120) and AMD ROCm 7 (Strix Halo gfx1151, RX 7900 XTX gfx1100, R9700 gfx1201) with zero-dependency $ORIGIN RPATH bundling.
Updated 2026-08-30 16:02:00 -09:00
Updated 2026-08-26 10:15:42 -09:00
Production-ready Proxmox LXC local AI serving stack: Qwen3.8-27B + embeddings + reranker on Strix Halo iGPU + RX 7900 XTX via OCuLink (ROCmFPX/llama.cpp, nested Podman, health-gated updates)
Updated 2026-08-24 14:26:47 -09:00
Production-grade evaluation framework & turnkey GitHub Action for benchmarking AI coding harnesses (Claude Code, Gemini CLI, Antigravity, OpenCode, DeepSeek), Model Context Protocol (MCP) servers, LSP diagnostics, and agent plugins across CoderEval & Terminal-Bench.
Updated 2026-08-22 11:33:17 -09:00
Open-source Claude Code plugin marketplace framework and distribution CLI deploying fast quality guardrails (ruff, pyright, biome, clippy), MCP tools, and language packs.
Updated 2026-08-20 10:18:07 -09:00
Xposed Module that unlocks and adds unique features to the Grindr app
Updated 2026-08-14 00:03:26 -09:00
Updated 2026-08-13 07:55:40 -09:00
Unified LLM infrastructure, build registries, Docker compose stacks, and VRAM estimation tools
Updated 2026-08-13 07:20:21 -09:00