try fix model loading quen3.6-35b

packages/node/meshnet_node/model_backend.py

@@ -134,8 +134,9 @@ class TorchModelShard:
                     self.model.to(self.device)
         except Exception as exc:
             if _looks_like_oom(exc):
+                memory_kind = "VRAM" if self.device.type == "cuda" else "RAM"
                 raise InsufficientVRAMError(
-                    f"insufficient VRAM to load {model_id} layers {shard_start}:{shard_end} "
+                    f"insufficient {memory_kind} to load {model_id} layers {shard_start}:{shard_end} "
                     f"with {quantization} quantization; choose a smaller shard or lower quantization"
                 ) from exc
             raise
@@ -411,7 +412,7 @@ def _should_partial_materialize_shard(
         return False
     if total_layers_hint is None:
         return False
-    return not (shard_start == 0 and shard_end >= total_layers_hint - 1)
+    return True
 
 
 def _load_partial_model_from_snapshot(
@@ -476,7 +477,7 @@ def _load_partial_model_from_snapshot(
         )
 
     with init_empty_weights_fn():
-        model = auto_model_for_causal_lm.from_config(cfg, torch_dtype=dtype)
+        model = auto_model_for_causal_lm.from_config(_causal_lm_config(cfg), torch_dtype=dtype)
     tie_weights = getattr(model, "tie_weights", None)
     if callable(tie_weights):
         tie_weights()
@@ -498,7 +499,7 @@ def _load_partial_model_from_snapshot(
             for tensor_name in names:
                 set_tensor_fn(
                     model,
-                    tensor_name,
+                    _checkpoint_tensor_name_for_model(model, tensor_name),
                     device,
                     value=handle.get_tensor(tensor_name),
                     dtype=dtype,
@@ -569,38 +570,74 @@ def _native_torch_dtype(cfg: Any, torch: Any) -> Any:
     return torch.bfloat16
 
 
+def _causal_lm_config(cfg: Any) -> Any:
+    """Use the text decoder config for composite VLM/MoE presets."""
+    get_text_config = getattr(cfg, "get_text_config", None)
+    if callable(get_text_config):
+        try:
+            return get_text_config()
+        except Exception:
+            pass
+    text_config = getattr(cfg, "text_config", None)
+    if text_config is not None:
+        return text_config
+    return cfg
+
+
+def _checkpoint_tensor_name_for_model(model: Any, tensor_name: str) -> str:
+    """Map multimodal checkpoint keys onto text-only CausalLM modules when needed."""
+    inner = getattr(model, "model", None)
+    if inner is not None and hasattr(inner, "language_model"):
+        return tensor_name
+    if ".language_model." in tensor_name:
+        return tensor_name.replace(".language_model.", ".")
+    return tensor_name
+
+
+def _transformer_backbone(model: Any) -> Any:
+    if hasattr(model, "model"):
+        inner = model.model
+        language_model = getattr(inner, "language_model", None)
+        if language_model is not None:
+            return language_model
+        return inner
+    if hasattr(model, "transformer"):
+        return model.transformer
+    raise ModelBackendError(
+        "unsupported HuggingFace model architecture: no transformer backbone found"
+    )
+
+
 def _model_layers(model: Any) -> Any:
-    if hasattr(model, "model") and hasattr(model.model, "layers"):
-        return model.model.layers
-    if hasattr(model, "transformer") and hasattr(model.transformer, "h"):
-        return model.transformer.h
+    backbone = _transformer_backbone(model)
+    for attr in ("layers", "h", "blocks"):
+        layers = getattr(backbone, attr, None)
+        if layers is not None:
+            return layers
     raise ModelBackendError(
         "unsupported HuggingFace model architecture: no transformer layers found"
     )
 
 
 def _embed_tokens(model: Any) -> Any:
-    if hasattr(model, "model") and hasattr(model.model, "embed_tokens"):
-        return model.model.embed_tokens
-    if hasattr(model, "transformer") and hasattr(model.transformer, "wte"):
-        return model.transformer.wte
+    backbone = _transformer_backbone(model)
+    for attr in ("embed_tokens", "wte"):
+        embed = getattr(backbone, attr, None)
+        if embed is not None:
+            return embed
     raise ModelBackendError(
         "unsupported HuggingFace model architecture: no token embeddings found"
     )
 
 
 def _position_embeddings(model: Any) -> Any | None:
-    if hasattr(model, "transformer") and hasattr(model.transformer, "wpe"):
-        return model.transformer.wpe
-    return None
+    backbone = _transformer_backbone(model)
+    return getattr(backbone, "wpe", None)
 
 
 def _rotary_embedding_module(model: Any) -> Any | None:
-    if hasattr(model, "model") and hasattr(model.model, "rotary_emb"):
-        return model.model.rotary_emb
-    if hasattr(model, "transformer") and hasattr(model.transformer, "rotary_emb"):
-        return model.transformer.rotary_emb
-    return None
+    backbone = _transformer_backbone(model)
+    return getattr(backbone, "rotary_emb", None)
 
 
 def _active_modules_for_shard(model: Any, shard_start: int, shard_end: int) -> list[Any]:
@@ -627,10 +664,11 @@ def _active_modules_for_shard(model: Any, shard_start: int, shard_end: int) -> l
 
 
 def _final_norm(model: Any) -> Any | None:
-    if hasattr(model, "model") and hasattr(model.model, "norm"):
-        return model.model.norm
-    if hasattr(model, "transformer") and hasattr(model.transformer, "ln_f"):
-        return model.transformer.ln_f
+    backbone = _transformer_backbone(model)
+    for attr in ("norm", "ln_f", "final_layer_norm"):
+        norm = getattr(backbone, attr, None)
+        if norm is not None:
+            return norm
     return None
 
 
@@ -743,7 +781,12 @@ def _looks_like_oom(exc: BaseException) -> bool:
     current: BaseException | None = exc
     while current is not None:
         text = str(current).lower()
-        if "out of memory" in text or "cuda error: out of memory" in text:
+        if (
+            "out of memory" in text
+            or "cuda error: out of memory" in text
+            or "paging file is too small" in text
+            or "os error 1455" in text
+        ):
             return True
         current = current.__cause__ or current.__context__
     return False

packages/node/meshnet_node/startup.py

@@ -995,6 +995,20 @@ def run_startup(
     )
     if user_pinned_shard:
         shard_label = f"{shard_label} (pinned)"
+    if user_pinned_shard and assigned_total_layers and assignment_bytes_per_layer:
+        pinned_layers = shard_end - shard_start + 1
+        max_layers = _max_assignable_layers(
+            memory_budget_mb,
+            assigned_total_layers,
+            assignment_bytes_per_layer,
+        )
+        if pinned_layers > max_layers:
+            raise ValueError(
+                f"Pinned shard layers {shard_start}–{shard_end} ({pinned_layers} layers) exceed "
+                f"the {memory_budget_mb / 1024:.1f} GB {memory_budget_source} budget "
+                f"(fits up to {max_layers}/{assigned_total_layers} layers at bfloat16). "
+                "Drop --shard-start/--shard-end to let the tracker auto-assign, or pin a smaller range."
+            )
     print(f"  Shard: {shard_label}", flush=True)
 
     # 4. Download shard
@@ -1020,7 +1034,77 @@ def run_startup(
     )
     print(f"  Cached at: {shard_path}", flush=True)
 
-    # 5. Start HTTP server
+    # 5. Start HTTP server — real HF weights use TorchNodeServer; stub-model stays stub.
+    _node_start_time = time.monotonic()
+    if hf_repo and assigned_model != "stub-model":
+        print("Loading real PyTorch model shard...", flush=True)
+        node = TorchNodeServer(
+            host=host,
+            port=port,
+            model_id=hf_repo,
+            shard_start=shard_start,
+            shard_end=shard_end,
+            quantization=quantization,
+            tracker_url=tracker_url,
+            route_timeout=route_timeout,
+            cache_dir=shard_path,
+            debug=debug,
+            max_loaded_shards=max_loaded_shards,
+        )
+        actual_port = node.start()
+        total_layers = getattr(getattr(node, "backend", None), "total_layers", None) or assigned_total_layers
+        shard_label = _format_shard_label(shard_start, shard_end, total_layers, model_name=assigned_model)
+        if user_pinned_shard:
+            shard_label = f"{shard_label} (pinned)"
+        public_host = advertise_host or (socket.getfqdn() if host == "0.0.0.0" else host)
+        endpoint = f"http://{public_host}:{actual_port}"
+        local_base_url = f"http://127.0.0.1:{actual_port}"
+        relay_bridge, relay_fields = _start_relay_bridge_if_available(
+            tracker_url,
+            address,
+            local_base_url,
+            endpoint,
+            relay_url=relay_url,
+        )
+        _attach_relay_bridge(node, relay_bridge)
+        reg_payload = {
+            "endpoint": endpoint,
+            "model": assigned_model,
+            "hf_repo": hf_repo,
+            "num_layers": total_layers,
+            "shard_start": shard_start,
+            "shard_end": shard_end,
+            "downloaded_models": downloaded_models,
+            "hardware_profile": hw,
+            "wallet_address": address,
+            "quantization": quantization,
+            "score": 1.0,
+            "tracker_mode": (shard_start == 0),
+            "managed_assignment": not user_pinned_shard,
+            "model_metadata": model_metadata_for(hf_repo, total_layers, cache_dir=shard_path),
+            **registration_capabilities,
+            **relay_fields,
+        }
+        tracker_node_id = _register_with_tracker(
+            tracker_url, reg_payload, node, _node_start_time,
+        )
+        print(
+            f"\n{'=' * 32}\n"
+            f"meshnet-node ready\n"
+            f"  Wallet:       {address}\n"
+            f"  Model ID:     {hf_repo}\n"
+            f"  Shard:        {shard_label}\n"
+            f"  {_shard_budget_line(memory_budget_mb, memory_budget_source, total_layers, quantization, bytes_per_layer=assignment_bytes_per_layer)}\n"
+            f"  Quantization: {quantization}\n"
+            f"  Endpoint:     {endpoint}\n"
+            f"  Node ID:      {tracker_node_id or 'unregistered'}\n"
+            f"  Hardware:     {_hardware_label(device, gpu_name)}\n"
+            f"  Benchmark:    {bench_tps:,.0f} (throughput index)\n"
+            f"{'=' * 32}",
+            flush=True,
+        )
+        return node
+
     is_last = shard_end >= assignment.get("model_layers_end", shard_end)
     node = StubNodeServer(
         host=host,
@@ -1031,7 +1115,6 @@ def run_startup(
         model=assigned_model,
         shard_path=shard_path,
     )
-    _node_start_time = time.monotonic()
     actual_port = node.start()
     public_host = advertise_host or (socket.getfqdn() if host == "0.0.0.0" else host)
     endpoint = f"http://{public_host}:{actual_port}"