ginnoir/homelabstack
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
154 Commits 1 Branch 0 Tags
98c4a2a02bfabd5c6c9ab546d2ab2052ba0fa0d1
Commit Graph
4 Commits
Author SHA1 Message Date
ginnoirandClaude Opus 4.8 98c4a2a02b docs: implementation plan for Hermes ecosystem integrations 
Phased, reversible plan. Phase 1 (acp-skill + curator-evolver, report-only)
fully actionable; Phases 2-3 (camofox stack, eagle-eye trial, UI) gated on
the spec's open decisions.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-27 05:18:21 -05:00
ginnoir b7ff9b2411 docs: add R730XD post-migration task plan 2026-06-27 05:05:30 -05:00
ginnoirandClaude Opus 4.8 8e7682985d feat(llm): add llama.cpp inference stack for Hermes (Qwen2.5-14B on P100) 
New stacks/llm/ serves Qwen2.5-14B-Instruct (Q4_K_M GGUF) via llama.cpp's
OpenAI-compatible server on the Tesla P100 (CDI nvidia.com/gpu=0), published on
172.20.0.1:8090 for the host-side Hermes agent. vLLM was rejected: the P100
(cc 6.0) lacks the DP4A INT8 instructions its AWQ/GPTQ kernels need.

Includes design spec and implementation plan under docs/superpowers/.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-26 16:22:57 -05:00
ginnoirandClaude Opus 4.8 c5d487effe chore: add migration helper scripts + cutover plan doc 
R510 -> R730XD/Proxmox migration helpers (consistent DB dumps, B2/Kopia snapshot refresh, cutover final backup) plus the previously-untracked gitea-portainer-registry cutover plan under docs/.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-17 23:27:55 -05:00