fix: add runtime shim for split_torch_state_dict_into_shards to unblock diffusers import

server.py

@@ -81,6 +81,19 @@ def get_model():
             # Ensure HF token env var is where downstream libs expect it
             if os.environ.get("HUGGINGFACEHUB_API_TOKEN") and not os.environ.get("HUGGINGFACE_HUB_TOKEN"):
                 os.environ["HUGGINGFACE_HUB_TOKEN"] = os.environ["HUGGINGFACEHUB_API_TOKEN"]
+
+            # Backward-compat shim: some diffusers versions import a helper only present in newer hub versions.
+            try:
+                import huggingface_hub as _hfh  # type: ignore
+
+                if not hasattr(_hfh, "split_torch_state_dict_into_shards"):
+                    def _split_torch_state_dict_into_shards(state_dict, max_shard_size="10GB"):
+                        # Minimal shim: return a single shard mapping expected by callers
+                        return {"pytorch_model.bin": state_dict}
+
+                    _hfh.split_torch_state_dict_into_shards = _split_torch_state_dict_into_shards  # type: ignore[attr-defined]
+            except Exception:
+                pass
             
             # Import here to defer importing diffusers/transformers until needed
             from infer_full import StableHair  # noqa: WPS433