[Bugfix] fix sleepmode level2 e2e test (#4019)

### What this PR does / why we need it?

enable sleepmode level2 e2e test and add the check logic to ensure the
nz is not enabled.

### Does this PR introduce _any_ user-facing change?

no

### How was this patch tested?

use e2e tests


- vLLM version: v0.11.0
- vLLM main:
83f478bb19

Signed-off-by: wangx700 <wangxin700@huawei.com>

.github/workflows/_e2e_test.yaml

@@ -182,7 +182,7 @@ jobs:
           pytest -sv tests/e2e/multicard/test_torchair_graph_mode.py
           pytest -sv tests/e2e/multicard/test_data_parallel.py
           pytest -sv tests/e2e/multicard/test_expert_parallel.py
-          # pytest -sv tests/e2e/multicard/test_external_launcher.py
+          pytest -sv tests/e2e/multicard/test_external_launcher.py
           pytest -sv tests/e2e/multicard/test_single_request_aclgraph.py
           pytest -sv tests/e2e/multicard/test_fused_moe_allgather_ep.py
           pytest -sv tests/e2e/multicard/test_ilama_lora_tp2.py

tests/e2e/multicard/test_external_launcher.py

@@ -108,6 +108,7 @@ def test_moe_external_launcher(model):
     assert proc.returncode == 0
 
 
+@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_NZ": "0"})
 def test_external_launcher_and_sleepmode():
     script = Path(
         __file__
@@ -154,6 +155,7 @@ def test_external_launcher_and_sleepmode():
     assert proc.returncode == 0
 
 
+@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_NZ": "0"})
 def test_external_launcher_and_sleepmode_level2():
     script = Path(
         __file__

tests/e2e/singlecard/test_camem.py

@@ -18,6 +18,8 @@
 #
 
 import gc
+import os
+from unittest.mock import patch
 
 import torch
 from vllm import SamplingParams
@@ -71,6 +73,7 @@ def test_basic_camem():
 
 
 @fork_new_process_for_each_test
+@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_NZ": "0"})
 def test_end_to_end():
     free, total = torch.npu.mem_get_info()
     used_bytes_baseline = total - free  # in case other process is running

tests/ut/worker/test_worker_v1.py

@@ -1,3 +1,4 @@
+import os
 import unittest
 from unittest.mock import MagicMock, patch
 
@@ -273,6 +274,7 @@ class TestNPUWorker(TestBase):
 
     @patch("vllm_ascend.worker.worker_v1.sleep_mode_enabled")
     @patch("vllm_ascend.worker.worker_v1.CaMemAllocator")
+    @patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_NZ": "0"})
     def test_wake_up_mode_enabled(self, mock_allocator_class,
                                   mock_sleep_mode_enabled):
         """Test wake_up method when sleep mode is enabled"""
@@ -295,6 +297,7 @@ class TestNPUWorker(TestBase):
             mock_allocator.wake_up.assert_called_once_with(tags=["test_tag"])
 
     @patch("vllm_ascend.worker.worker_v1.sleep_mode_enabled")
+    @patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_NZ": "0"})
     def test_wake_up_mode_disabled_raises_error(self, mock_sleep_mode_enabled):
         """Test wake_up method raises exception when sleep mode is disabled"""
         from vllm_ascend.worker.worker_v1 import NPUWorker

vllm_ascend/worker/worker_v1.py

@@ -47,7 +47,7 @@ from vllm_ascend.cpu_binding import bind_cpus
 from vllm_ascend.device_allocator.camem import CaMemAllocator
 from vllm_ascend.distributed.parallel_state import init_ascend_model_parallel
 from vllm_ascend.platform import NPUPlatform
-from vllm_ascend.utils import (init_ascend_soc_version,
+from vllm_ascend.utils import (init_ascend_soc_version, is_enable_nz,
                                prefill_context_parallel_enable,
                                register_ascend_customop, sleep_mode_enabled,
                                try_register_lib, vllm_version_is)
@@ -184,6 +184,11 @@ class NPUWorker(WorkerBase):
             raise ValueError(
                 "Sleep mode is not enabled. Please compile vllm-ascend with COMPILE_CUSTOM_KERNELS=1."
             )
+
+        if is_enable_nz():
+            raise ValueError(
+                "FRACTAL_NZ mode is enabled. This may cause model parameter precision issues "
+                "in the RL scenarios. Please set VLLM_ASCEND_ENABLE_NZ=0.")
         allocator = CaMemAllocator.get_instance()
         allocator.wake_up(tags=tags)