upgrade to vllm 0.11.2 (#4400)

Bump vLLM version to v0.11.2

What's broken and changed by vLLM:
1. structured_output is broken by
https://github.com/vllm-project/vllm/pull/26866
2. get_mrope_input_positions is broken by
https://github.com/vllm-project/vllm/pull/28399
3. graph mode is broken by
https://github.com/vllm-project/vllm/pull/25110 we'll upgrade torch to
2.8 to fix the problem later
4. embedding is broken by
https://github.com/vllm-project/vllm/pull/27583
5. `get_attn_backend_cls` and attention backend is broken are broken by
https://github.com/vllm-project/vllm/pull/28534
6. spec decode is broken by
https://github.com/vllm-project/vllm/pull/28771
7. sp feature is broken by
https://github.com/vllm-project/vllm/pull/27126
8. mtp is broken by https://github.com/vllm-project/vllm/pull/27922
9. lora is broken by https://github.com/vllm-project/vllm/pull/21068
10. execute_model is broken by
https://github.com/vllm-project/vllm/pull/26866
11. `VLLM_DISABLE_SHARED_EXPERTS_STREAM` env is broken by
https://github.com/vllm-project/vllm/pull/28159
12. kv cahe is broken by https://github.com/vllm-project/vllm/pull/27753
13. dp is broken by https://github.com/vllm-project/vllm/pull/25110

 
What's broken and changed by ourself:
1. qwen vl is broken by https://github.com/vllm-project/vllm/pull/28455
We'll remove model files in the future to avoid this kind of error
2. Engine core is broken by
https://github.com/vllm-project/vllm/pull/23691 We'll remove the patch
file in the future.
3. Ascend scheduler is broken by
https://github.com/vllm-project/vllm/pull/28733 We'll remove ascend
scheudler later.
4. qwen3-next is broken by
https://github.com/vllm-project/vllm/pull/28083 We'll remove model files
in the future to avoid this kind of error
5. qwen vl is broken by https://github.com/vllm-project/vllm/pull/27764.
We'll remove model files in the future

Known issue:
1. ray doesn't work 
2. the accuracy of qwen3-next is not correct
3. qwen3-vl is broken
4. prefix cache+ ascend scheduler + deepseek v2 lite is broken.

Co-authored-by: MengqingCao <cmq0113@163.com>
Co-authored-by: hfadzxy <starmoon_zhang@163.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: 22dimensions <waitingwind@foxmail.com>
Co-authored-by: shen-shanshan <467638484@qq.com>


- vLLM version: v0.11.2

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
Signed-off-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: MengqingCao <cmq0113@163.com>
Co-authored-by: hfadzxy <starmoon_zhang@163.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>

vllm_ascend/worker/worker_v1.py

@@ -18,7 +18,8 @@
 #
 
 import copy
-from typing import Optional, Union
+from types import NoneType
+from typing import Optional
 
 import torch
 import torch.nn as nn
@@ -37,7 +38,7 @@ from vllm.sequence import IntermediateTensors
 from vllm.tasks import SupportedTask
 from vllm.utils.mem_constants import GiB_bytes
 from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
-from vllm.v1.core.sched.output import SchedulerOutput
+from vllm.v1.core.sched.output import GrammarOutput, SchedulerOutput
 from vllm.v1.kv_cache_interface import KVCacheConfig, KVCacheSpec
 from vllm.v1.outputs import (EMPTY_MODEL_RUNNER_OUTPUT, AsyncModelRunnerOutput,
                              DraftTokenIds, ModelRunnerOutput)
@@ -206,6 +207,14 @@ class NPUWorker(WorkerBase):
         device = torch.device(f"npu:{self.local_rank}")
         NPUPlatform.set_device(device)
         NPUPlatform.empty_cache()
+
+        visible_device_count = (torch.npu.device_count()
+                                if torch.npu.is_available() else 0)
+        assert self.parallel_config.local_world_size <= visible_device_count, (
+            f"local_world_size ({self.parallel_config.local_world_size}) must be "
+            f"less than or equal to the number of visible devices "
+            f"({visible_device_count}).")
+
         self.init_npu_memory = NPUPlatform.mem_get_info()[0]
         # Initialize the distributed environment.
         self._init_worker_distributed_environment()
@@ -266,7 +275,7 @@ class NPUWorker(WorkerBase):
     def execute_model(
         self,
         scheduler_output: "SchedulerOutput",
-    ) -> Optional[Union[ModelRunnerOutput, AsyncModelRunnerOutput]]:
+    ) -> ModelRunnerOutput | None:
         # enable msMonitor to monitor the performance of vllm-ascend
         if envs_ascend.MSMONITOR_USE_DAEMON:
             dp.step()
@@ -280,7 +289,7 @@ class NPUWorker(WorkerBase):
 
         output = self.model_runner.execute_model(scheduler_output,
                                                  intermediate_tensors)
-        if isinstance(output, (ModelRunnerOutput, AsyncModelRunnerOutput)):
+        if isinstance(output, (ModelRunnerOutput, NoneType)):
             return output
 
         assert isinstance(output, IntermediateTensors)
@@ -304,6 +313,12 @@ class NPUWorker(WorkerBase):
         output.kv_connector_output = kv_connector_output
         return output
 
+    @torch.inference_mode()
+    def sample_tokens(
+        self, grammar_output: "GrammarOutput"
+    ) -> ModelRunnerOutput | AsyncModelRunnerOutput:
+        return self.model_runner.sample_tokens(grammar_output)
+
     def load_model(self) -> None:
         if self.vllm_config.model_config.enable_sleep_mode:
             allocator = CaMemAllocator.get_instance()