feat: checkpoint distributed gguf runtime stories

packages/node/meshnet_node/model_backend.py

@@ -323,6 +323,10 @@ class TorchModelShard:
             )
         self.is_head = shard_start == 0
         self.is_tail = shard_end >= self.total_layers - 1
+        self.loaded_shard_start = shard_start
+        self.loaded_shard_end = shard_end
+        self.owns_embedding = self.is_head
+        self.owns_final_head = self.is_tail
         self.hidden_size = int(
             getattr(self.model.config, "hidden_size", 0)
             or getattr(self.model.config, "n_embd", 0)
@@ -344,6 +348,17 @@ class TorchModelShard:
             ttl_seconds=float(os.environ.get("MESHNET_KV_TTL_SECONDS", "600")),
         )
 
+    @property
+    def loaded_range(self) -> tuple[int, int]:
+        return self.loaded_shard_start, self.loaded_shard_end
+
+    @property
+    def endpoint_ownership(self) -> dict[str, bool]:
+        return {
+            "owns_embedding": self.owns_embedding,
+            "owns_final_head": self.owns_final_head,
+        }
+
     def encode_prompt(self, prompt: str, session_id: str | None = None) -> TensorPayload:
         if not self.is_head or self._embed_tokens is None:
             raise ModelBackendError("text prompts can only be accepted by the head shard")