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

server/pyproject.toml

@@ -118,7 +118,7 @@ addopts = "-ra -q --disable-pytest-warnings --cov --cov-report html -v"
 testpaths = ["tests"]
 asyncio_mode = "auto"
 markers = [
-    "gpu_modal: mark test to run only with GPU Modal endpoints (deselect with '-m \"not gpu_modal\"')",
+    "model_api: tests for the unified model-serving HTTP API (backend- and hardware-agnostic)",
 ]
 
 [tool.ruff.lint]
@@ -130,7 +130,7 @@ select = [
 
 [tool.ruff.lint.per-file-ignores]
 "reflector/processors/summary/summary_builder.py" = ["E501"]
-"gpu/**.py" = ["PLC0415"]
+"gpu/modal_deployments/**.py" = ["PLC0415"]
 "reflector/tools/**.py" = ["PLC0415"]
 "migrations/versions/**.py" = ["PLC0415"]
 "tests/**.py" = ["PLC0415"]