Launch: Make exllamav2 requirement more friendly

Add the ability to use an unsafe config flag if needed and migrate
the exl2 check to a different file within the exl2 backend code.

Signed-off-by: kingbri <bdashore3@proton.me>

backends/exllamav2/utils.py

@@ -0,0 +1,31 @@
+from packaging import version
+from importlib.metadata import version as package_version
+
+from common.logger import init_logger
+
+logger = init_logger(__name__)
+
+
+def check_exllama_version():
+    """Verifies the exllama version"""
+
+    required_version = "0.0.12"
+    current_version = package_version("exllamav2").split("+")[0]
+
+    if version.parse(current_version) < version.parse(required_version):
+        raise SystemExit(
+            f"ERROR: TabbyAPI requires ExLlamaV2 {required_version} "
+            f"or greater. Your current version is {current_version}.\n"
+            "Please upgrade your environment by running a start script "
+            "(start.bat or start.sh)\n\n"
+            "Or you can manually run a requirements update "
+            "using the following command:\n\n"
+            "For CUDA 12.1:\n"
+            "pip install --upgrade -r requirements.txt\n\n"
+            "For CUDA 11.8:\n"
+            "pip install --upgrade -r requirements-cu118.txt\n\n"
+            "For ROCm:\n"
+            "pip install --upgrade -r requirements-amd.txt\n\n"
+        )
+    else:
+        logger.info(f"ExllamaV2 version: {current_version}")