feat: self-hosted gpu api (#636)

* Self-hosted gpu api

* Refactor self-hosted api

* Rename model api tests

* Use lifespan instead of startup event

* Fix self hosted imports

* Add newlines

* Add response models

* Move gpu dir to the root

* Add project description

* Refactor lifespan

* Update env var names for model api tests

* Preload diarizarion service

* Refactor uploaded file paths

gpu/self_hosted/runserver.sh

@@ -0,0 +1,17 @@
+#!/bin/sh
+set -e
+
+export PATH="/root/.local/bin:$PATH"
+cd /app
+
+# Install Python dependencies at runtime (first run or when FORCE_SYNC=1)
+if [ ! -d "/app/.venv" ] || [ "$FORCE_SYNC" = "1" ]; then
+  echo "[startup] Installing Python dependencies with uv..."
+  uv sync --compile-bytecode --locked
+else
+  echo "[startup] Using existing virtual environment at /app/.venv"
+fi
+
+exec uv run uvicorn main:app --host 0.0.0.0 --port 8000
+
+