[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/sfa_v1.py

@@ -5,7 +5,6 @@ import torch
 import torch_npu
 import vllm.envs as envs_vllm
 from torch import nn
-from vllm.attention.backends.abstract import AttentionBackend, MLAAttentionImpl
 from vllm.config import CUDAGraphMode, VllmConfig, get_current_vllm_config
 from vllm.distributed import get_tensor_model_parallel_world_size, get_tp_group
 from vllm.forward_context import get_forward_context
@@ -13,7 +12,6 @@ from vllm.logger import logger
 from vllm.model_executor.layers.linear import UnquantizedLinearMethod
 from vllm.triton_utils import HAS_TRITON
 from vllm.v1.attention.backends.mla.common import MLACommonMetadataBuilder
-from vllm.v1.attention.backends.utils import AttentionCGSupport
 from vllm.v1.kv_cache_interface import AttentionSpec
 
 from vllm_ascend import envs
@@ -34,11 +32,20 @@ from vllm_ascend.ops.triton.rope import rope_forward_triton
 from vllm_ascend.ops.weight_prefetch import maybe_npu_prefetch
 from vllm_ascend.quantization.w8a8 import AscendW8A8LinearMethod
 from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_ND, _round_up, dispose_layer,
-                               enable_dsa_cp, maybe_trans_nz)
+                               enable_dsa_cp, maybe_trans_nz, vllm_version_is)
 from vllm_ascend.worker.npu_input_batch import NPUInputBatch
 
+# isort: off
 if TYPE_CHECKING:
     from vllm.v1.core.sched.output import SchedulerOutput
+if vllm_version_is('0.13.0'):
+    from vllm.v1.attention.backends.utils import AttentionCGSupport
+    from vllm.attention.backends.abstract import (  # type: ignore
+        AttentionBackend, MLAAttentionImpl)
+else:
+    from vllm.v1.attention.backend import (  # type: ignore
+        AttentionBackend, AttentionCGSupport, MLAAttentionImpl)
+# isort: on
 
 
 class AscendSFABackend(AttentionBackend):