feat: add new cuda profile

Author: jaluma

docker-compose.yaml

@@ -48,6 +48,26 @@ services:
     profiles:
       - llamacpp-cpu
 
+  # Private-GPT service for the local mode (with CUDA support)
+  # This service builds from a local Dockerfile and runs the application in local mode.
+  private-gpt-llamacpp-cuda:
+    image: ${PGPT_IMAGE:-zylonai/private-gpt}${PGPT_TAG:-0.6.1}-llamacpp-cuda
+    build:
+      context: .
+      dockerfile: Dockerfile.llamacpp-cuda
+    volumes:
+      - ./local_data/:/home/worker/app/local_data
+      - ./models/:/home/worker/app/models
+    entrypoint: sh -c ".venv/bin/python scripts/setup && .venv/bin/python -m private_gpt"
+    ports:
+      - "8001:8001"
+    environment:
+      PORT: 8001
+      PGPT_PROFILES: local
+      HF_TOKEN: ${HF_TOKEN}
+    profiles:
+      - llamacpp-cuda
+
   #-----------------------------------
   #---- Ollama services --------------
   #-----------------------------------

fern/docs/pages/quickstart/quickstart.mdx

@@ -82,6 +82,21 @@ HF_TOKEN=<your_hf_token> docker-compose --profile llamacpp-cpu up
 ```
 Replace `<your_hf_token>` with your actual Hugging Face token.
 
+#### 2. LlamaCPP CUDA
+
+**Description:**
+This profile runs the Private-GPT services locally using `llama-cpp` and Hugging Face models.
+
+**Requirements:**
+A **Hugging Face Token (HF_TOKEN)** is required for accessing Hugging Face models. Obtain your token following [this guide](/installation/getting-started/troubleshooting#downloading-gated-and-private-models).
+
+**Run:**
+Start the services with your Hugging Face token using pre-built images:
+```sh
+HF_TOKEN=<your_hf_token> docker-compose --profile llamacpp-cuda up
+```
+Replace `<your_hf_token>` with your actual Hugging Face token.
+
 ## Building Locally
 
 If you prefer to build Docker images locally, which is useful when making changes to the codebase or the Dockerfiles, follow these steps: