feat: add Unsloth Studio configuration and docker-compose support

.env.example

@@ -50,6 +50,20 @@ LLAMA_SWAP_IMAGE="ghcr.io/mostlygeek/llama-swap:${LLAMA_SWAP_VERSION}"
 LLAMA_SWAP_PORT="8080"
 LLAMA_SWAP_API_KEY="${LLAMA_API_KEY}"
 
+# -----------------------------------------------------------------------------
+# Unsloth Studio
+# -----------------------------------------------------------------------------
+UNSLOTH_IMAGE="unsloth/unsloth:latest"
+UNSLOTH_CONTAINER_NAME="unsloth"
+UNSLOTH_WORK_DIR="${MODELS_ROOT}/unsloth"
+HF_CACHE_DIR="${MODELS_ROOT}/models"
+UNSLOTH_BIND_ADDRESS="0.0.0.0"
+UNSLOTH_STUDIO_HOST_PORT="8000"
+UNSLOTH_JUPYTER_HOST_PORT="8888"
+UNSLOTH_STUDIO_PASSWORD=""
+JUPYTER_PASSWORD=""
+UNSLOTH_STUDIO_BOOTSTRAP_TIMEOUT="3600"
+
 # -----------------------------------------------------------------------------
 # Service lifecycle
 # -----------------------------------------------------------------------------

README.md

@@ -89,6 +89,22 @@ Files:
 | `docker-compose.yml` | GPU-enabled llama.cpp build service |
 | `build-llama.cpp.sh` | Pull source and run containerized build |
 
+### Unsloth Studio
+
+`docker-compose.unsloth.yml` runs the official NVIDIA image with Unsloth Studio
+and JupyterLab. Configure the `UNSLOTH_*` values in `.env`, set
+`UNSLOTH_STUDIO_PASSWORD` and `JUPYTER_PASSWORD`, then start it with:
+
+```bash
+docker compose -f docker-compose.unsloth.yml up -d
+```
+
+Studio is available at `http://<server-host>:8000`; JupyterLab is available at
+`http://<server-host>:8888`. The service persists the Hugging Face cache,
+Studio data, Triton kernels, and files under `UNSLOTH_WORK_DIR`. The published
+ports default to `0.0.0.0`; set `UNSLOTH_BIND_ADDRESS="127.0.0.1"` when using
+SSH port forwarding instead of exposing the services to the LAN.
+
 The image includes `libssl-dev`, so llama.cpp can download Hugging Face models over HTTPS.
 
 ## Scripts

docker-compose.unsloth.yml

@@ -0,0 +1,32 @@
+services:
+  unsloth:
+    image: ${UNSLOTH_IMAGE:-unsloth/unsloth:latest}
+    container_name: ${UNSLOTH_CONTAINER_NAME:-unsloth}
+    gpus: all
+    ipc: host
+    stop_grace_period: 150s
+    restart: unless-stopped
+    ulimits:
+      memlock:
+        soft: -1
+        hard: -1
+      stack:
+        soft: 67108864
+        hard: 67108864
+    ports:
+      - "${UNSLOTH_BIND_ADDRESS:-0.0.0.0}:${UNSLOTH_STUDIO_HOST_PORT:-8000}:8000"
+      - "${UNSLOTH_BIND_ADDRESS:-0.0.0.0}:${UNSLOTH_JUPYTER_HOST_PORT:-8888}:8888"
+    environment:
+      HF_TOKEN: ${HF_TOKEN:-}
+      JUPYTER_PASSWORD: ${JUPYTER_PASSWORD:-}
+      UNSLOTH_STUDIO_PASSWORD: ${UNSLOTH_STUDIO_PASSWORD:-}
+      UNSLOTH_STUDIO_BOOTSTRAP_TIMEOUT: ${UNSLOTH_STUDIO_BOOTSTRAP_TIMEOUT:-3600}
+    volumes:
+      - ${UNSLOTH_WORK_DIR:-./unsloth-work}:/workspace/host
+      - ${HF_CACHE_DIR:-./huggingface-cache}:/workspace/.cache/huggingface
+      - unsloth-studio:/opt/unsloth-studio
+      - unsloth-triton:/workspace/.cache/triton
+
+volumes:
+  unsloth-studio:
+  unsloth-triton: