vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

feat(homepage): split AI fleet into role-based groups on a dedicated AI tab

Browse Source 
Move the ~22-service flat "AI Systems" group off the Main tab into a new
four-tab layout (Main / AI / Infrastructure / Toolchain). The AI tab sorts
the inference fleet by function into seven groups:

  AI - Inference        gen, char-rp, char-rp-reasoning, Granite summarizer
  AI - Eval & Retrieval Selene, Skywork Reward, Qwen3 rerank/embed, image-bench
  AI - Gateways & Chat  LiteLLM, Asset Engine, Gateway Chat, Open WebUI, ...
  AI - Speech (TTS)     Chatterbox Fast, Kokoro, mOrpheus
  AI - Audio Tools      Parakeet ASR, YT Voice Clipper
  AI - Image & Media    ComfyUI, Arbo
  AI - Dormant          stopped rollback seats + retired auditions

Relabel each stack's homepage.group so canonical stacks/ matches the live
containers on ana-ml2, ana-docker, and irv-ml1. Dormant stacks were refreshed
with `docker compose up --no-start` so they carry the new label while staying
stopped (compose-start rollback preserved). settings.yaml drives tab/order/
columns; services.yaml and README updated to the new scheme.
This commit is contained in:
vh
2026-07-14 20:05:50 -07:00
parent 982c319d9f
commit 569e1af9ca
23 changed files with 113 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
stacks/arbo/compose.yaml
+1 -1
View File
@@ -85,7 +85,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Image & Media
- homepage.name=Arbo
- homepage.icon=mdi-image-multiple-outline
- homepage.description=Catalog-driven ComfyUI engine (irv-ml1)
stacks/asset-engine/compose.yaml
+1 -1
View File
@@ -53,7 +53,7 @@ services:
retries: 3
start_period: 30s
labels:
- homepage.group=AI Systems
- homepage.group=AI - Gateways & Chat
- homepage.name=Asset Engine
- homepage.icon=mdi-tools
- homepage.description=Control plane over the PFI inference fleet
stacks/char-rp-gguf/compose.yaml
+2 -2
View File
@@ -88,7 +88,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Inference
- homepage.name=char-rp (Magidonia-24B GGUF)
- homepage.icon=mdi-drama-masks
- homepage.description=Dark-romantasy RP prose seat, non-thinking (llama.cpp, ana-ml2 GPU 0)
@@ -169,7 +169,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Dormant
- homepage.name=char-rp-reasoning (QwQ-32B RpR-v4 GGUF)
- homepage.icon=mdi-brain
- homepage.description=Dark-romantasy RP reasoning seat, managed CoT (llama.cpp, ana-ml2 GPU 0)
stacks/chatterbox/compose.yaml
+1 -1
View File
@@ -67,7 +67,7 @@ services:
# warms torch.compile — give it a generous deadline.
start_period: 600s
labels:
- homepage.group=AI Systems
- homepage.group=AI - Speech (TTS)
- homepage.name=Chatterbox Turbo
- homepage.icon=mdi-account-music-outline
- homepage.description=Low-latency English TTS w/ voice cloning + paralinguistics (irv-ml1)
stacks/comfyui/compose.yaml
+1 -1
View File
@@ -86,7 +86,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Image & Media
- homepage.name=ComfyUI
- homepage.icon=mdi-image-auto-adjust
- homepage.description=Node-based SD/Flux inference (irv-ml1)
stacks/cosyvoice/compose.yaml
+1 -1
View File
@@ -53,7 +53,7 @@ services:
# First boot pulls ~2–3 GB of model weights.
start_period: 300s
labels:
- homepage.group=AI Systems
- homepage.group=AI - Dormant
- homepage.name=CosyVoice
- homepage.icon=mdi-account-voice
- homepage.description=Expressive multilingual TTS + cloning (irv-ml1)
stacks/fish-s2/compose.yaml
+1 -1
View File
@@ -98,7 +98,7 @@ services:
# checkpoint load. Generous deadline.
start_period: 900s
labels:
- homepage.group=AI Systems
- homepage.group=AI - Dormant
- homepage.name=Fish Audio S2-Pro
- homepage.icon=mdi-fish
- homepage.description=Most expressive open-source TTS — 15k+ paralinguistic tags, voice cloning, 80+ languages (irv-ml1)
stacks/gateway-chat/compose.yaml
+1 -1
View File
@@ -25,7 +25,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Gateways & Chat
- homepage.name=Gateway Chat
- homepage.icon=mdi-chat-processing
- homepage.description=Light web chat for smoking LiteLLM gateway models (auto-discovery, system prompts, vision)
stacks/index-tts/compose.yaml
+1 -1
View File
@@ -56,7 +56,7 @@ services:
# CUDA warmup. Generous deadline to ride that out.
start_period: 600s
labels:
- homepage.group=AI Systems
- homepage.group=AI - Dormant
- homepage.name=IndexTTS-2
- homepage.icon=mdi-account-music
- homepage.description=Emotion-controllable TTS w/ voice cloning (irv-ml1)
stacks/kokoro/compose.yaml
+1 -1
View File
@@ -61,7 +61,7 @@ services:
retries: 3
start_period: 90s
labels:
- homepage.group=AI Systems
- homepage.group=AI - Speech (TTS)
- homepage.name=Kokoro
- homepage.icon=mdi-microphone-message
- homepage.description=Low-latency English TTS w/ streaming (irv-ml1)
stacks/litellm/compose.yaml
+1 -1
View File
@@ -69,7 +69,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Gateways & Chat
- homepage.name=LiteLLM Gateway
- homepage.icon=mdi-router-network
- homepage.description=vLLM request/response logging gateway (ana-docker)
stacks/mOrpheus/compose.yaml
+1 -1
View File
@@ -82,7 +82,7 @@ services:
retries: 3
start_period: 60s
labels:
- homepage.group=AI Systems
- homepage.group=AI - Speech (TTS)
- homepage.name=mOrpheus TTS
- homepage.icon=mdi-account-voice
- homepage.description=Uncensored Orpheus TTS (baddy + zero-shot clone), real-time, irv-ml1
stacks/omnivoice/compose.yaml
+1 -1
View File
@@ -49,7 +49,7 @@ services:
# First boot: OmniVoice + Whisper ASR pre-warm + cloning every staged voice.
start_period: 1200s
labels:
- homepage.group=AI Systems
- homepage.group=AI - Dormant
- homepage.name=OmniVoice
- homepage.icon=mdi-account-voice
- homepage.description=Zero-shot multilingual voice-cloning TTS, OpenAI /v1/audio/speech (irv-ml1, 3090)
stacks/parakeet/compose.yaml
+1 -1
View File
@@ -46,7 +46,7 @@ services:
# First boot may include a ~400 MB model download.
start_period: 300s
labels:
- homepage.group=AI Systems
- homepage.group=AI - Audio Tools
- homepage.name=Parakeet ASR
- homepage.icon=mdi-microphone
- homepage.description=Parakeet-TDT speech-to-text via sherpa-onnx (irv-ml1)
stacks/qwen-image-bench/compose.yaml
+1 -1
View File
@@ -72,7 +72,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Eval & Retrieval
- homepage.name=Qwen-Image-Bench (T2I judge, NVFP4)
- homepage.icon=mdi-image-check
- homepage.description=Qwen text-to-image quality judge (NVFP4, vision-intact) on ana-ml2 GPU 1
stacks/qwen36-27b-aeon/compose.yaml
+2 -2
View File
@@ -121,7 +121,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Inference
- homepage.name=Qwen3.6-27B AEON (NVFP4, vision) — gen
- homepage.icon=mdi-creation
- homepage.description=Uncensored Qwen3.6-27B multimodal NVFP4, the `gen` model (ana-ml2 GPU 0)
@@ -202,7 +202,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Dormant
- homepage.name=Qwen3.6-27B AEON RP (NVFP4 + MTP) — char-rp
- homepage.icon=mdi-drama-masks
- homepage.description=Uncensored Qwen3.6-27B, native MTP single-seat RP (char-rp), ana-ml2 GPU 0
stacks/qwopus3.5-122b/compose.yaml
+1 -1
View File
@@ -96,7 +96,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Dormant
- homepage.name=Qwopus3.5-122B-A10B (abliterated NVFP4, vision)
- homepage.icon=mdi-creation
- homepage.description=Kimi-distilled abliterated Qwen3.5-122B-A10B NVFP4, vision-intact, the `gen` model (ana-ml2 GPU 0)
stacks/selene/compose.yaml
+1 -1
View File
@@ -74,7 +74,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Eval & Retrieval
- homepage.name=Selene 1 Mini 8B (judge, FP8)
- homepage.icon=mdi-gavel
- homepage.description=AtlaAI Selene 1 Mini Llama-3.1-8B judge (FP8) via vLLM (ana-ml2 GPU1)
stacks/skaldsong/compose.yaml
+1 -1
View File
@@ -109,7 +109,7 @@ services:
retries: 3
start_period: 30s
labels:
- homepage.group=AI Systems
- homepage.group=AI - Gateways & Chat
- homepage.name=Skaldsong
- homepage.icon=mdi-book-edit-outline
- homepage.description=Wizard + reader surface for multi-agent storytelling (Bifrost consumer of Worldtree)
stacks/vllm/compose.yaml
+4 -4
View File
@@ -77,7 +77,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Eval & Retrieval
- homepage.name=vLLM Embed (Qwen3)
- homepage.icon=mdi-vector-arrange-below
- homepage.description=Qwen3 Embedding via vLLM (ana-ml2)
@@ -133,7 +133,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Eval & Retrieval
- homepage.name=vLLM Rerank (Qwen3)
- homepage.icon=mdi-sort-variant
- homepage.description=Qwen3 Reranker via vLLM (ana-ml2)
@@ -191,7 +191,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Eval & Retrieval
- homepage.name=vLLM Reward (Skywork)
- homepage.icon=mdi-scale-balance
- homepage.description=Skywork-Reward-V2 8B classifier via vLLM (ana-ml2)
@@ -266,7 +266,7 @@ services:
networks:
- tnet
labels:
- homepage.group=AI Systems
- homepage.group=AI - Inference
- homepage.name=vLLM Granite 4.1 8B (summarizer)
- homepage.icon=mdi-text-box-outline
- homepage.description=Granite 4.1 8B FP8 via vLLM (ana-ml2)