From f37bd76fed2043964a5c3fe6ba7bc11e4aab4bf0 Mon Sep 17 00:00:00 2001
From: tocmo <tocmo@localhost>
Date: Sun, 5 Apr 2026 01:57:51 -0400
Subject: [PATCH] Fix GPU setup: check and install nvidia-container-toolkit

dupfinder-setup.sh now verifies nvidia-container-toolkit is present
when a GPU is detected. If missing, prints install instructions and
offers to install it automatically (adds NVIDIA repo, installs toolkit,
configures Docker runtime, restarts Docker).

Without this toolkit Docker silently falls back to CPU even when a
GPU is present and the compose file has the device reservation.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 debian/files/opt/dupfinder/dupfinder-setup.sh | 37 ++++++++++++++++++-
 1 file changed, 35 insertions(+), 2 deletions(-)

diff --git a/debian/files/opt/dupfinder/dupfinder-setup.sh b/debian/files/opt/dupfinder/dupfinder-setup.sh
index f7e758d..1181779 100644
--- a/debian/files/opt/dupfinder/dupfinder-setup.sh
+++ b/debian/files/opt/dupfinder/dupfinder-setup.sh
@@ -53,12 +53,45 @@ if ! docker compose version &>/dev/null; then
 fi
 ok "docker compose V2 available"
 
-# ── Check NVIDIA GPU ──────────────────────────────────────────────────────────
+# ── Check NVIDIA GPU + container toolkit ─────────────────────────────────────
 info "Checking GPU..."
 if command -v nvidia-smi &>/dev/null && nvidia-smi &>/dev/null; then
     GPU_NAME=$(nvidia-smi --query-gpu=name --format=csv,noheader 2>/dev/null | head -1)
     ok "NVIDIA GPU detected: $GPU_NAME"
-    GPU_AVAILABLE=true
+
+    # nvidia-container-toolkit is required for Docker GPU passthrough
+    if ! command -v nvidia-ctk &>/dev/null && ! dpkg -l nvidia-container-toolkit &>/dev/null 2>&1; then
+        echo ""
+        echo "    nvidia-container-toolkit is not installed."
+        echo "    Without it Docker cannot pass the GPU to the container."
+        echo "    Install with:"
+        echo ""
+        echo "      curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg"
+        echo "      curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list"
+        echo "      sudo apt update && sudo apt install -y nvidia-container-toolkit"
+        echo "      sudo nvidia-ctk runtime configure --runtime=docker"
+        echo "      sudo systemctl restart docker"
+        echo ""
+        read -rp "    Install nvidia-container-toolkit now? (Y/n): " INST_CTK
+        if [[ "$INST_CTK" != "n" && "$INST_CTK" != "N" ]]; then
+            curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \
+                | gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
+            curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \
+                | sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' \
+                | tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
+            apt update -qq && apt install -y nvidia-container-toolkit
+            nvidia-ctk runtime configure --runtime=docker
+            systemctl restart docker
+            ok "nvidia-container-toolkit installed and Docker restarted"
+        else
+            echo "    Skipping — GPU will not be available in Docker. You can re-run setup later."
+            GPU_AVAILABLE=false
+        fi
+    else
+        ok "nvidia-container-toolkit is present"
+    fi
+
+    [[ "$GPU_AVAILABLE" != "false" ]] && GPU_AVAILABLE=true
 else
     echo "    No NVIDIA GPU detected — will use CPU for perceptual hashing"
     GPU_AVAILABLE=false