fix: reconcile legacy branch runtime with current GGUF

packages/node/meshnet_node/torch_server.py

@@ -19,6 +19,7 @@ from .model_backend import (
     InsufficientVRAMError,
     KVCacheMiss,
     MissingModelDependencyError,
+    Quantization,
     TailTokenResult,
     TorchModelShard,
     _tensor_from_bfloat16_bytes,
@@ -45,7 +46,7 @@ class _DirectRequestUncertainError(ConnectionError):
     """A direct request may have reached the downstream node but did not finish."""
 
 
-from .server import (  # noqa: E402
+from .server import (
     _WIRE_VERSION,
     _parse_shape,
     _validate_activation_body,
@@ -398,7 +399,7 @@ class _TorchHandler(http.server.BaseHTTPRequestHandler):
     # Finite responses below provide Content-Length; streams are chunked.
     protocol_version = "HTTP/1.1"
 
-    def log_message(self, fmt, *args):  # suppress request logs in tests
+    def log_message(self, fmt, *args):  # noqa: suppress request logs in tests
         pass
 
     def _request_id(self) -> str: