Mikei386
7c5bbe2ffb
- POST /v1/images/generations (OpenAI-kompatibel, prompt/size/n/seed/quality) - quality: standard=30 Steps (Default), high=50 Steps - Größen: 1024x1024, 1536x1024, 1024x1536, 1920x1088, 1088x1920 - GPU-Hotswap: Qwen stoppen -> FLUX laden -> Bild -> FLUX entladen -> Qwen wiederherstellen (exakt vorheriges Profil) - Zentrales GPU/Modell-Lock (Profilwechsel und Bild teilen sich das Lock) - Chat-Requests warten während Bild-Job (kein 502), Timeout CHAT_WAIT_TIMEOUT - Robuste Recovery: try/finally, Worker-Beendigung, VRAM-Check, Qwen-Readiness - /status: image.phase, image.worker, image.model_loaded, qwen.available, qwen.active_chats - GET /images, GET /images/<datei> (validiert, nur images/-Verzeichnis) - image_worker.py: FLUX-Worker (eigener Prozess, JSON-Protokoll, bf16 + enable_model_cpu_offload) - deploy: venv (torch/diffusers/transformers/accelerate), Modell-Download, Image-Dir, systemd-Unit mit Image-Umgebungsvariablen - dev: Mock-Worker, fake-systemctl, Benchmarks (GPU-Resident, Offload, Steps, Quality-Compare), 32 lokale Tests - README: Bildgenerierung, Hotswap, Recovery, Benchmarks (RTX 5080), Python-Pakete Benchmarks (RTX 5080, 16 GB, CPU-Offload): - 512x512 / 10 Steps: ~9.3 s - 1024x1024 / 30 Steps: ~31.3 s - 1024x1024 / 50 Steps: ~45.3 s - 1920x1088 / 50 Steps: ~91 s - Peak-VRAM: ~8.4-8.9 GB - Hotswap-Gesamtzeit: ~41-42 s (1024x1024 / 30 Steps)
85 lines
3.0 KiB
Bash
Executable File
85 lines
3.0 KiB
Bash
Executable File
#!/bin/bash
|
||
# AI Profile Router – Installation/Update auf dem Zielsystem.
|
||
# Wird als root auf dem Zielsystem ausgeführt (per SSH, vgl. deploy.sh).
|
||
# Erwartet ai_profile_router.py, image_worker.py und mike-ai-profile-router.service
|
||
# im selben Verzeichnis wie dieses Skript.
|
||
set -euo pipefail
|
||
|
||
DIR="$(cd "$(dirname "$0")" && pwd)"
|
||
INSTALL_DIR=/opt/mike-ai/ai-profile-router
|
||
SERVICE=mike-ai-profile-router.service
|
||
OLD_SERVICE=mike-ai-local-llm-router.service
|
||
OLD_DIR=/opt/mike-ai/local-llm-router
|
||
BACKUP_DIR=/opt/mike-ai/.backup-ai-profile-router-$(date +%Y%m%d-%H%M%S)
|
||
VENV="$INSTALL_DIR/venv"
|
||
MODEL_DIR=/opt/mike-ai/models/FLUX.2-klein-base-4B
|
||
IMAGE_DIR="$INSTALL_DIR/images"
|
||
|
||
echo "== AI Profile Router: Installation/Update =="
|
||
|
||
# --- 1. Bestehenden (alten) Router entfernen, mit Backup -------------------
|
||
if [ -f "/etc/systemd/system/${OLD_SERVICE}" ]; then
|
||
echo "-- Entferne alten Router ${OLD_SERVICE} (Backup: ${BACKUP_DIR})"
|
||
mkdir -p "$BACKUP_DIR"
|
||
systemctl stop "$OLD_SERVICE" 2>/dev/null || true
|
||
systemctl disable "$OLD_SERVICE" 2>/dev/null || true
|
||
mv "/etc/systemd/system/${OLD_SERVICE}" "$BACKUP_DIR/"
|
||
if [ -d "$OLD_DIR" ]; then
|
||
mv "$OLD_DIR" "$BACKUP_DIR/local-llm-router"
|
||
fi
|
||
else
|
||
echo "-- Kein alter Router gefunden"
|
||
fi
|
||
|
||
# --- 2. Neue Dateien installieren -------------------------------------------
|
||
mkdir -p "$INSTALL_DIR" "$IMAGE_DIR"
|
||
install -m 0755 "$DIR/ai_profile_router.py" "$INSTALL_DIR/ai_profile_router.py"
|
||
install -m 0755 "$DIR/image_worker.py" "$INSTALL_DIR/image_worker.py"
|
||
install -m 0644 "$DIR/${SERVICE}" "/etc/systemd/system/${SERVICE}"
|
||
|
||
# --- 3. Python-Venv mit Bild-Abhängigkeiten ---------------------------------
|
||
if [ ! -x "$VENV/bin/python" ]; then
|
||
echo "-- Erstelle Python-Venv in $VENV"
|
||
python3 -m venv "$VENV"
|
||
fi
|
||
echo "-- Installiere/aktualisiere Bild-Abhängigkeiten (torch, diffusers, ...)"
|
||
"$VENV/bin/pip" install --quiet --upgrade pip
|
||
"$VENV/bin/pip" install --quiet \
|
||
torch \
|
||
diffusers \
|
||
transformers \
|
||
accelerate
|
||
|
||
# --- 4. FLUX-Modell (nur wenn noch nicht vorhanden) --------------------------
|
||
if [ -f "$MODEL_DIR/model_index.json" ]; then
|
||
echo "-- FLUX-Modell vorhanden: $MODEL_DIR"
|
||
else
|
||
echo "-- Lade FLUX.2-klein-base-4B nach $MODEL_DIR (kann dauern)"
|
||
"$VENV/bin/python" - <<'PY'
|
||
import os
|
||
from huggingface_hub import snapshot_download
|
||
snapshot_download(
|
||
repo_id="black-forest-labs/FLUX.2-klein-base-4B",
|
||
local_dir="/opt/mike-ai/models/FLUX.2-klein-base-4B",
|
||
local_dir_use_symlinks=False,
|
||
)
|
||
print("Modell-Download abgeschlossen")
|
||
PY
|
||
fi
|
||
|
||
# --- 5. Service aktivieren und starten ---------------------------------------
|
||
systemctl daemon-reload
|
||
systemctl enable "$SERVICE"
|
||
systemctl restart "$SERVICE"
|
||
|
||
# --- 6. Verifikation ----------------------------------------------------------
|
||
sleep 1
|
||
if ! systemctl is-active --quiet "$SERVICE"; then
|
||
echo "-- FEHLER: Service läuft nicht" >&2
|
||
journalctl -u "$SERVICE" -n 20 --no-pager >&2
|
||
exit 1
|
||
fi
|
||
echo "-- Service läuft"
|
||
curl -sf "http://127.0.0.1:8081/status" | python3 -m json.tool
|
||
echo "== Fertig =="
|