From 16f601c7d7a16bfc27e2942fbdebf9e1cfddac4d Mon Sep 17 00:00:00 2001
From: mattiasghodsian <mattiasghodsian@gmail.com>
Date: Mon, 23 Mar 2026 09:53:13 +0100
Subject: [PATCH] feat: NVIDIA GPU Docker support with compose override (#93)

* feat: nvidia gpu config for docker

* refactor: split NVIDIA GPU support into compose override

Address review feedback:
- Revert --engine ollama from base Dockerfile CMD (breaks non-Ollama users)
- Keep bookworm pin and OLLAMA_HOST fix in base config
- Move GPU-specific config (/proc, /sys mounts, deploy.resources.reservations)
  into new docker-compose.gpu.nvidia.yml override, matching the existing ROCm
  pattern (docker-compose.gpu.rocm.yml)
- Restore Ollama port to standard 11434
- Remove commented-out GPU blocks from base docker-compose.yml
- Add Ollama healthcheck with depends_on condition to base compose
- Remove run.sh from repo root
- Rewrite README Docker section to document CPU, NVIDIA, and ROCm patterns

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Jon Saad-Falcon <41205309+jonsaadfalcon@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 README.md                                   | 22 +++++++++++++++
 deploy/docker/Dockerfile                    |  4 +--
 deploy/docker/docker-compose.gpu.nvidia.yml | 31 +++++++++++++++++++++
 deploy/docker/docker-compose.yml            | 15 ++++++----
 4 files changed, 65 insertions(+), 7 deletions(-)
 create mode 100644 deploy/docker/docker-compose.gpu.nvidia.yml

diff --git a/README.md b/README.md
index 39f3f0a5..0b885e24 100644
--- a/README.md
+++ b/README.md
@@ -68,6 +68,28 @@ uv run jarvis doctor
 
 `jarvis init` auto-detects your hardware and recommends the best engine. After init, it prints engine-specific next steps. Run `uv run jarvis doctor` at any time to diagnose configuration or connectivity issues.
 
+## Docker
+
+A Docker Compose configuration bundles Jarvis with Ollama:
+
+```bash
+# CPU-only (default)
+docker compose -f deploy/docker/docker-compose.yml up -d
+
+# NVIDIA GPU (requires NVIDIA Container Toolkit)
+docker compose -f deploy/docker/docker-compose.yml \
+  -f deploy/docker/docker-compose.gpu.nvidia.yml up -d
+
+# AMD GPU (requires ROCm)
+docker compose -f deploy/docker/docker-compose.yml \
+  -f deploy/docker/docker-compose.gpu.rocm.yml up -d
+
+# Pull a model into Ollama
+docker compose -f deploy/docker/docker-compose.yml exec ollama ollama pull qwen3:8b
+```
+
+Services: Jarvis on `:8000`, Ollama on `:11434`.
+
 ## Development
 
 From source, you need to make sure Rust is installed on System:
diff --git a/deploy/docker/Dockerfile b/deploy/docker/Dockerfile
index 4f5b8291..6e1f1e50 100644
--- a/deploy/docker/Dockerfile
+++ b/deploy/docker/Dockerfile
@@ -8,7 +8,7 @@ COPY frontend/ .
 RUN npm run build
 
 # Stage 2: Build Python package
-FROM python:3.12-slim AS builder
+FROM python:3.12-slim-bookworm AS builder
 
 WORKDIR /app
 COPY pyproject.toml README.md ./
@@ -21,7 +21,7 @@ RUN pip install --no-cache-dir uv && \
     uv pip install --system ".[server]"
 
 # Stage 3: Runtime
-FROM python:3.12-slim
+FROM python:3.12-slim-bookworm
 
 COPY --from=builder /usr/local /usr/local
 COPY --from=builder /app /app
diff --git a/deploy/docker/docker-compose.gpu.nvidia.yml b/deploy/docker/docker-compose.gpu.nvidia.yml
new file mode 100644
index 00000000..22dcb450
--- /dev/null
+++ b/deploy/docker/docker-compose.gpu.nvidia.yml
@@ -0,0 +1,31 @@
+# NVIDIA GPU override — use with:
+#   docker compose -f deploy/docker/docker-compose.yml -f deploy/docker/docker-compose.gpu.nvidia.yml up
+
+services:
+  jarvis:
+    build:
+      context: ../..
+      dockerfile: deploy/docker/Dockerfile.gpu
+    volumes:
+      - /proc:/proc:ro
+      - /sys:/sys:ro
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+
+  ollama:
+    image: ollama/ollama:latest
+    environment:
+      - NVIDIA_VISIBLE_DEVICES=all
+      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
diff --git a/deploy/docker/docker-compose.yml b/deploy/docker/docker-compose.yml
index a19268ef..284f0897 100644
--- a/deploy/docker/docker-compose.yml
+++ b/deploy/docker/docker-compose.yml
@@ -1,5 +1,3 @@
-version: "3.9"
-
 services:
   jarvis:
     build:
@@ -9,17 +7,24 @@ services:
       - "8000:8000"
     environment:
       - OPENJARVIS_ENGINE_DEFAULT=ollama
-      - OPENJARVIS_OLLAMA_HOST=http://ollama:11434
+      - OLLAMA_HOST=http://ollama:11434
     depends_on:
-      - ollama
+      ollama:
+        condition: service_healthy
     restart: unless-stopped
 
   ollama:
-    image: ollama/ollama
+    image: ollama/ollama:latest
     ports:
       - "11434:11434"
     volumes:
       - ollama-models:/root/.ollama
+    healthcheck:
+      test: ["CMD", "ollama", "list"]
+      interval: 5s
+      timeout: 3s
+      retries: 10
+      start_period: 10s
     restart: unless-stopped
 
 volumes: