relay working with qwen2.5;

relay anounced on node ready

tests/test_kv_cache_distributed.py

@@ -18,6 +18,7 @@ from meshnet_node.model_backend import (
     SessionCacheStore,
     TailTokenResult,
     TensorPayload,
+    TorchModelShard,
 )
 from meshnet_node.torch_server import TorchNodeServer
 
@@ -98,6 +99,40 @@ def test_drop_removes_session():
         store.lookup("s1")
 
 
+def test_prefill_cache_triton_cpu_failure_disables_cache_and_retries_stateless():
+    """CPU shards must recover when hybrid model cache path dispatches Triton."""
+    shard = object.__new__(TorchModelShard)
+    shard.model_id = "fake-hybrid"
+    shard.supports_kv_cache = True
+    shard._effective_start = lambda start_layer=None: 22
+    shard._new_session_cache = lambda: object()
+
+    calls = []
+
+    def fake_run_layers(hidden_states, attention_mask, position_ids, *, start_layer=None, cache=None, past_len=0):
+        calls.append({"cache": cache, "past_len": past_len})
+        if cache is not None:
+            raise RuntimeError("Pointer argument cannot be accessed from Triton (cpu tensor?)")
+        return "stateless-ok"
+
+    shard._run_layers = fake_run_layers
+
+    result = TorchModelShard._run_layers_session(
+        shard,
+        hidden_states=object(),
+        attention_mask=None,
+        position_ids=None,
+        session_id="session-1",
+        cache_mode="prefill",
+    )
+
+    assert result == "stateless-ok"
+    assert shard.supports_kv_cache is False
+    assert len(calls) == 2
+    assert calls[0]["cache"] is not None
+    assert calls[1]["cache"] is None
+
+
 # ---------------------------------------------------------------------------
 # HTTP session protocol with fake cached backends
 # ---------------------------------------------------------------------------