[Main2Main] Upgrade vllm commit to 0113 (#5839)

### What this PR does / why we need it?
Upgrade vllm commit to 0113 (11b6af5280d6d6dfb8953af16e67b25f819b3be9)

- Modify import paths due to the refactors
https://github.com/vllm-project/vllm/pull/31916
https://github.com/vllm-project/vllm/pull/32054

- Fix `TypeError: NPUOffloadingSpec.__init__() takes 2 positional
arguments but 3 were given` due to
https://github.com/vllm-project/vllm/pull/24498

- Skip the async-scheduling tests in
`tests/e2e/multicard/4-cards/long_sequence/test_mtp.py`, which are never
verified
https://github.com/vllm-project/vllm/pull/31998

- Skip some pooling tests, which are caused by
https://github.com/vllm-project/vllm/pull/32148
where vllm is also failed
https://buildkite.com/vllm/ci/builds/46705/steps/canvas?jid=019bb329-3834-4685-862b-1613b8e0f5d4

We will reopen those tests when main2main reachs
https://github.com/vllm-project/vllm/pull/32243

- Skip some cases in
`tests/e2e/multicard/4-cards/long_sequence/test_mtp.py`, which are
broken by
https://github.com/vllm-project/vllm/pull/32118

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

### How was this patch tested?

- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef

Signed-off-by: wjunLu <wjunlu217@gmail.com>
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
Co-authored-by: hfadzxy <starmoon_zhang@163.com>

vllm_ascend/kv_offload/npu.py

@@ -2,7 +2,6 @@ from collections.abc import Iterator
 from typing import Optional
 
 import torch
-from vllm.attention.backends.abstract import AttentionBackend
 from vllm.config import VllmConfig
 from vllm.v1.kv_offload.abstract import LoadStoreSpec, OffloadingManager
 from vllm.v1.kv_offload.backends.cpu import CPUBackend
@@ -10,14 +9,28 @@ from vllm.v1.kv_offload.lru_manager import LRUOffloadingManager
 from vllm.v1.kv_offload.mediums import CPULoadStoreSpec, GPULoadStoreSpec
 from vllm.v1.kv_offload.spec import OffloadingSpec
 from vllm.v1.kv_offload.worker.worker import OffloadingHandler
+from vllm.v1.kv_cache_interface import KVCacheConfig
 
 from vllm_ascend.kv_offload.cpu_npu import CpuNpuOffloadingHandler
+from vllm_ascend.utils import vllm_version_is
+
+# isort: off
+if vllm_version_is('0.13.0'):
+    from vllm.attention.backends.abstract import AttentionBackend  # type: ignore
+else:
+    from vllm.v1.attention.backend import AttentionBackend  # type: ignore
+# isort: on
 
 
 class NPUOffloadingSpec(OffloadingSpec):
 
-    def __init__(self, vllm_config: VllmConfig):
-        super().__init__(vllm_config)
+    def __init__(self,
+                 vllm_config: VllmConfig,
+                 kv_cache_config: Optional[KVCacheConfig] = None):
+        if vllm_version_is('0.13.0'):
+            super().__init__(vllm_config)
+        else:
+            super().__init__(vllm_config, kv_cache_config)
 
         num_cpu_blocks = self.extra_config.get("num_cpu_blocks")
         if not num_cpu_blocks: