[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/attention/attention_v1.py

@@ -22,15 +22,9 @@ from typing import ClassVar, List, Optional, Tuple, Type
 import torch
 import torch_npu
 import vllm.envs as envs_vllm
-from vllm.attention.backends.abstract import (AttentionBackend, AttentionImpl,
-                                              AttentionLayer, AttentionType)
-from vllm.attention.backends.registry import (AttentionBackendEnum,
-                                              register_backend)
 from vllm.config import VllmConfig, get_current_vllm_config
 from vllm.forward_context import ForwardContext, get_forward_context
 from vllm.utils.math_utils import cdiv
-from vllm.v1.attention.backends.utils import (AttentionCGSupport,
-                                              AttentionMetadataBuilder)
 from vllm.v1.core.sched.output import SchedulerOutput
 from vllm.v1.kv_cache_interface import AttentionSpec, CrossAttentionSpec
 
@@ -45,7 +39,23 @@ from vllm_ascend.compilation.acl_graph import (
     update_draft_graph_params_workspaces, update_graph_params_workspaces)
 from vllm_ascend.device.device_op import DeviceOperator
 from vllm_ascend.ops.flashcomm2_oshard_manager import flashcomm2_oshard_manager
-from vllm_ascend.utils import weak_ref_tensors
+from vllm_ascend.utils import vllm_version_is, weak_ref_tensors
+
+# isort: off
+if vllm_version_is('0.13.0'):
+    from vllm.v1.attention.backends.utils import (AttentionCGSupport,
+                                                  AttentionMetadataBuilder)
+    from vllm.attention.backends.abstract import (  # type: ignore
+        AttentionBackend, AttentionImpl, AttentionLayer, AttentionType)
+    from vllm.attention.backends.registry import (  # type: ignore
+        AttentionBackendEnum, register_backend)
+else:
+    from vllm.v1.attention.backend import (  # type: ignore
+        AttentionBackend, AttentionCGSupport, AttentionImpl, AttentionLayer,
+        AttentionType, AttentionMetadataBuilder)
+    from vllm.v1.attention.backends.registry import (  # type: ignore
+        AttentionBackendEnum, register_backend)
+# isort: on
 
 # default max value of sliding window size
 SWA_INT_MAX = 2147483647