Merge pull request #393 from mefich/main

Unloading vision model of VLMs for Exllamav3 backend

Author: kingbri1

backends/exllamav3/model.py

@@ -563,6 +563,10 @@ async def unload(self, loras_only: bool = False, **kwargs):
                 self.draft_config = None
                 self.draft_cache = None
 
+            if self.use_vision:
+                self.vision_model.unload()
+                self.vision_model = None
+
             # Cleanup the generator from any pending jobs
             if self.generator is not None:
                 await self.generator.close()