refactor(mlx): move mlx_cache.py from common to mlx backend

The ThreadSafeLRUPromptCache is only used by the mlx backend. After
evaluating mlx-vlm, it was determined that the cache cannot be shared
because mlx-vlm's generate/stream_generate functions don't support
the prompt_cache parameter that mlx_lm provides.

- Move mlx_cache.py from backend/python/common/ to backend/python/mlx/
- Remove sys.path manipulation from backend.py and test.py
- Fix test assertion to expect "MLX model loaded successfully"

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <[email protected]>
Signed-off-by: Blightbow <[email protected]>

Author: blightbow

backend/python/mlx/backend.py

@@ -19,8 +19,6 @@
 import base64
 import io
 
-# Add common module to path for shared cache
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'common'))
 from mlx_cache import ThreadSafeLRUPromptCache
 
 _ONE_DAY_IN_SECONDS = 60 * 60 * 24

backend/python/common/mlx_cache.py backend/python/mlx/mlx_cache.pybackend/python/common/mlx_cache.py renamed to backend/python/mlx/mlx_cache.py

@@ -49,7 +49,7 @@ def test_load_model(self):
                 stub = backend_pb2_grpc.BackendStub(channel)
                 response = stub.LoadModel(backend_pb2.ModelOptions(Model="mlx-community/Llama-3.2-1B-Instruct-4bit"))
                 self.assertTrue(response.success)
-                self.assertEqual(response.message, "Model loaded successfully")
+                self.assertEqual(response.message, "MLX model loaded successfully")
         except Exception as err:
             print(err)
             self.fail("LoadModel service failed")
@@ -245,9 +245,6 @@ class TestThreadSafeLRUPromptCache(unittest.TestCase):
     """
 
     def setUp(self):
-        import sys
-        import os
-        sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', 'common'))
         from mlx_cache import ThreadSafeLRUPromptCache
         self.cache = ThreadSafeLRUPromptCache(max_size=3)