Add local GPU inference: auto-detect GPU, auto-download best diffusion models

Adds AI_PROVIDER=local_gpu — a fully self-contained GPU inference engine
using HuggingFace Diffusers that requires zero InvokeAI/ComfyUI setup.
All existing providers (InvokeAI, ComfyUI, OpenAI, Replicate) remain intact
and can be mixed with local GPU via per-operation overrides.

New features:
- GPU auto-detection (CUDA/NVIDIA, MPS/Apple Silicon, CPU fallback)
- VRAM-tiered model selection:
    ultra ≥16 GB → SDXL inpaint + SDXL base
    high  8-16 GB → SDXL inpaint + SDXL base
    medium 4-8 GB → SD 2.x inpaint + SD 2.1
    low  <4 GB   → SD 2.x (small)
- Auto-download model weights to HuggingFace disk cache at startup
  (background task; first request loads from local disk, not internet)
- LRU pipeline cache evicts oldest GPU pipeline when VRAM limit reached
- Per-operation model overrides via HF_MODEL_INPAINT / HF_MODEL_TXT2IMG etc.
- Optional HF_TOKEN for gated/private HuggingFace models

New files:
- backend/app/services/gpu_detect.py   — GPU detection + tier/model mapping
- backend/app/services/local_diffusion.py — Diffusers provider + LRU cache
- backend/app/routers/gpu_status.py    — GET /api/gpu/status, POST /api/gpu/prefetch
- backend/requirements.gpu.txt         — Diffusers ecosystem deps (GPU only)
- docker-compose.gpu.yml               — NVIDIA GPU compose (one-command startup)
- Dockerfile.gpu                       — pytorch/pytorch:2.1.0-cuda12.1 base image
- scripts/gpu_setup.py                 — Startup GPU info logger

Modified:
- backend/app/config.py                — local_gpu settings added
- backend/app/services/remote_provider.py — local_gpu registered as provider
- backend/app/routers/ai_tools.py      — /api/config exposes GPU tier + caps
- backend/app/main.py                  — GPU router + background prefetch task
- backend/entrypoint.sh                — runs gpu_setup.py at container start
- .env.example                         — local_gpu documented as first option

Quick start with GPU:
  docker compose -f docker-compose.gpu.yml up --build

https://claude.ai/code/session_01WVDg7amsy1TTtxvpku7bcM

scripts/gpu_setup.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+"""
+GPU setup script — runs at container startup.
+Detects GPU, logs capabilities, triggers background model prefetch when
+AI_PROVIDER=local_gpu and AUTO_DOWNLOAD_MODELS=true.
+Non-fatal: any failure just prints a warning.
+"""
+import os
+import sys
+
+
+def main():
+    print("Detecting GPU…")
+
+    backend = "cpu"
+    device_name = "CPU"
+    vram_gb = 0.0
+
+    try:
+        import torch
+
+        if torch.cuda.is_available():
+            backend = "cuda"
+            props = torch.cuda.get_device_properties(0)
+            device_name = props.name
+            vram_gb = props.total_memory / (1024 ** 3)
+            print(f"✓ CUDA GPU: {device_name} ({vram_gb:.1f} GB VRAM)")
+        elif hasattr(torch.backends, "mps") and torch.backends.mps.is_available():
+            backend = "mps"
+            device_name = "Apple Silicon"
+            print("✓ Apple Silicon MPS GPU detected")
+        else:
+            print("⚠ No GPU detected — AI_PROVIDER=local_gpu will use CPU (inference will be slow)")
+
+    except ImportError:
+        print("⚠ PyTorch not installed — GPU detection skipped")
+        return
+
+    provider = os.environ.get("AI_PROVIDER", "").lower()
+    if provider != "local_gpu":
+        print(f"  AI_PROVIDER={provider!r} — local GPU inference not active")
+        return
+
+    auto_dl = os.environ.get("AUTO_DOWNLOAD_MODELS", "true").lower()
+    if auto_dl != "true":
+        print("  AUTO_DOWNLOAD_MODELS=false — skipping model prefetch")
+        print("  Models will download on first request and cache to ~/.cache/huggingface")
+        return
+
+    # Determine tier for a helpful startup message
+    if vram_gb >= 16:
+        tier, models_hint = "ultra", "SDXL (best quality)"
+    elif vram_gb >= 8:
+        tier, models_hint = "high", "SDXL"
+    elif vram_gb >= 4:
+        tier, models_hint = "medium", "Stable Diffusion 2.x"
+    else:
+        tier, models_hint = "low", "Stable Diffusion 2.x (small)"
+
+    print(f"  GPU tier: {tier} → will use {models_hint} models")
+    print("  Models will auto-download on first request (~2–7 GB per pipeline).")
+    print("  To pre-download now: POST /api/gpu/prefetch")
+    print("  Check progress at:   GET  /api/gpu/prefetch-status")
+
+
+if __name__ == "__main__":
+    main()