From 66a0679e18fb1ab203dd2719aaa52084e303b56f Mon Sep 17 00:00:00 2001
From: JB <jb-apps@outlook.com>
Date: Sun, 5 Oct 2025 16:05:16 -0700
Subject: [PATCH] feat: Update Docker configuration for GPU support and remove
 deprecated compose file

---
 README.md                                     | 18 +++++++---------
 docker-compose.gpu.yml => docker-compose.yaml | 21 ++++++++++++-------
 2 files changed, 20 insertions(+), 19 deletions(-)
 rename docker-compose.gpu.yml => docker-compose.yaml (50%)

diff --git a/README.md b/README.md
index d6ae13c..865a3c9 100644
--- a/README.md
+++ b/README.md
@@ -53,24 +53,20 @@ Browse to http://localhost:8000. Uploaded source files are stored in `/data/uplo
 
 Set any of these with `-e VAR=value` when starting the container.
 
-### GPU-enabled build
-If you want CUDA acceleration inside the container, a GPU-aware Docker runtime (for example the NVIDIA Container Toolkit) is required. The repository ships an updated `abogen/Dockerfile` based on the CUDA runtime plus a helper Compose file.
+### Docker Compose (GPU by default)
+The repo includes `docker-compose.yaml`, which targets GPU hosts out of the box. Install the NVIDIA Container Toolkit and run:
 
 ```bash
-# Build the GPU image (installs the matching CUDA PyTorch wheel)
-docker compose -f docker-compose.gpu.yml build
-
-# Start the service with GPU access (--profile gpu in Compose v2 is optional)
-docker compose -f docker-compose.gpu.yml up -d
+docker compose up -d --build
 ```
 
-Useful overrides:
+Key build/runtime knobs:
 
-- `TORCH_VERSION` – pin a specific PyTorch release that matches your host driver (leave empty for latest).
-- `TORCH_INDEX_URL` – change the download index if you need a different CUDA build.
+- `TORCH_VERSION` – pin a specific PyTorch release that matches your driver (leave blank for the latest on the configured index).
+- `TORCH_INDEX_URL` – swap out the PyTorch download index when targeting a different CUDA build.
 - `ABOGEN_DATA` – host path that stores uploads/outputs (defaults to `./data`).
 
-The Compose file reserves a GPU via `device_requests`. Standard `docker run` works as well:
+CPU-only deployment: comment out the `deploy.resources.reservations.devices` block (and the optional `runtime: nvidia` line) inside the compose file. Compose will then run without requesting a GPU. If you prefer the classic CLI:
 
 ```bash
 docker build -f abogen/Dockerfile -t abogen-gpu .
diff --git a/docker-compose.gpu.yml b/docker-compose.yaml
similarity index 50%
rename from docker-compose.gpu.yml
rename to docker-compose.yaml
index f498225..8395d21 100644
--- a/docker-compose.gpu.yml
+++ b/docker-compose.yaml
@@ -1,3 +1,5 @@
+version: "3.9"
+
 services:
   abogen:
     build:
@@ -6,7 +8,7 @@ services:
       args:
         TORCH_INDEX_URL: ${TORCH_INDEX_URL:-https://download.pytorch.org/whl/cu124}
         TORCH_VERSION: ${TORCH_VERSION:-}
-    image: abogen-gpu:latest
+    image: abogen:latest
     ports:
       - "${ABOGEN_PORT:-8000}:8000"
     volumes:
@@ -16,15 +18,18 @@ services:
       ABOGEN_PORT: 8000
       ABOGEN_UPLOAD_ROOT: /data/uploads
       ABOGEN_OUTPUT_ROOT: /data/outputs
+    # --- GPU support -----------------------------------------------------
+    # These settings assume the NVIDIA Container Toolkit is installed.
+    # Leave them in place for GPU acceleration; comment out the entire block
+    # below if you are deploying to a CPU-only host.
     deploy:
       resources:
         reservations:
           devices:
-            - driver: nvidia
-              count: all
-              capabilities: [gpu]
-    device_requests:
-      - driver: nvidia
-        count: -1
-        capabilities: [gpu]
+            - capabilities: [gpu]
+              # driver: nvidia
+              # count: all
+    # Runtime flag is only honored by legacy docker-compose (v1) CLI.
+    # Uncomment if you're still using it:
+    # runtime: nvidia
     restart: unless-stopped