[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/distributed/kv_transfer/kv_p2p/mooncake_connector.py

@@ -43,13 +43,18 @@ from vllm.v1.request import RequestStatus
 from vllm_ascend.ascend_config import get_ascend_config, init_ascend_config
 from vllm_ascend.distributed.kv_transfer.utils.mooncake_transfer_engine import global_te
 from vllm_ascend.distributed.kv_transfer.utils.utils import get_transfer_timeout_value
-from vllm_ascend.utils import is_vl_model
+from vllm_ascend.utils import is_vl_model, vllm_version_is
 
+# isort: off
 if TYPE_CHECKING:
-    from vllm.attention.backends.abstract import AttentionMetadata
+    if vllm_version_is('0.13.0'):
+        from vllm.attention.backends.abstract import AttentionMetadata  # type: ignore
+    else:
+        from vllm.attention.backends import AttentionMetadata  # type: ignore
     from vllm.forward_context import ForwardContext
     from vllm.v1.core.kv_cache_manager import KVCacheBlocks
     from vllm.v1.request import Request
+# isort: on
 
 GET_META_MSG = b"get_meta_msg"
 DONE_RECVING_MSG = b"done_recving_msg"

vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake_layerwise_connector.py

@@ -38,13 +38,18 @@ from vllm_ascend.distributed.kv_transfer.utils.mooncake_transfer_engine import \
     global_te
 from vllm_ascend.distributed.kv_transfer.utils.utils import (
     align_memory, get_transfer_timeout_value, kv_alltoall_and_rearrange)
-from vllm_ascend.utils import npu_stream_switch
+from vllm_ascend.utils import npu_stream_switch, vllm_version_is
 
+# isort: off
 if TYPE_CHECKING:
-    from vllm.attention.backends.abstract import AttentionMetadata
+    if vllm_version_is('0.13.0'):
+        from vllm.attention.backends.abstract import AttentionMetadata  # type: ignore
+    else:
+        from vllm.attention.backends import AttentionMetadata  # type: ignore
     from vllm.forward_context import ForwardContext
     from vllm.v1.core.kv_cache_manager import KVCacheBlocks
     from vllm.v1.request import Request
+# isort: on
 
 DONE_SENDING_MSG = b"done_sending_msg"
 

vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/ascend_store_connector.py

@@ -3,7 +3,6 @@ from typing import Any, Optional
 
 import torch
 import zmq
-from vllm.attention.backends.abstract import AttentionMetadata
 from vllm.config import VllmConfig
 from vllm.distributed.kv_transfer.kv_connector.v1.base import (
     KVConnectorBase_V1, KVConnectorMetadata, KVConnectorRole)
@@ -20,6 +19,14 @@ from vllm_ascend.distributed.kv_transfer.kv_pool.ascend_store.pool_scheduler imp
     KVPoolScheduler, get_zmq_rpc_path_lookup)
 from vllm_ascend.distributed.kv_transfer.kv_pool.ascend_store.pool_worker import \
     KVPoolWorker
+from vllm_ascend.utils import vllm_version_is
+
+# isort: off
+if vllm_version_is('0.13.0'):
+    from vllm.attention.backends.abstract import AttentionMetadata  # type: ignore
+else:
+    from vllm.v1.attention.backend import AttentionMetadata  # type: ignore
+# isort: on
 
 
 class AscendStoreConnector(KVConnectorBase_V1):

vllm_ascend/distributed/kv_transfer/kv_pool/cpu_offload/cpu_offload_connector.py

@@ -9,7 +9,6 @@ from dataclasses import dataclass
 from typing import TYPE_CHECKING, Any, Optional, Sequence
 
 import torch
-from vllm.attention.backends.abstract import AttentionType
 from vllm.attention.layer import Attention, MLAAttention
 from vllm.config import VllmConfig, get_layers_from_vllm_config
 from vllm.distributed.ec_transfer import get_ec_transfer, has_ec_transfer
@@ -26,13 +25,25 @@ from vllm.v1.kv_cache_interface import (FullAttentionSpec, KVCacheSpec,
 
 from vllm_ascend.distributed.kv_transfer.kv_pool.ascend_store.metadata import (
     MetadataServer, MetadataServerProc, MLAConfig)
+from vllm_ascend.utils import vllm_version_is
+
+# isort: off
+if vllm_version_is('0.13.0'):
+    from vllm.attention.backends.abstract import AttentionType  # type: ignore
+else:
+    from vllm.v1.attention.backend import AttentionType  # type: ignore
 
 if TYPE_CHECKING:
-    from vllm.attention.backends.abstract import AttentionMetadata
+    if vllm_version_is('0.13.0'):
+        from vllm.attention.backends.abstract import \
+            AttentionMetadata  # type: ignore
+    else:
+        from vllm.v1.attention.backend import AttentionType  #type: ignore
     from vllm.forward_context import ForwardContext
     from vllm.v1.core.kv_cache_manager import KVCacheBlocks
     from vllm.v1.kv_cache_interface import KVCacheConfig
     from vllm.v1.request import Request
+# isort: on
 
 
 @dataclass

vllm_ascend/distributed/kv_transfer/ucm_connector.py

@@ -9,16 +9,23 @@ from vllm.distributed.kv_transfer.kv_connector.v1.base import (
 from vllm.logger import init_logger
 from vllm.v1.core.sched.output import SchedulerOutput
 
+from vllm_ascend.utils import vllm_version_is
+
 logger = init_logger(__name__)
 
+# isort: off
 if TYPE_CHECKING:
-    from vllm.attention.backends.abstract import AttentionMetadata
+    if vllm_version_is('0.13.0'):
+        from vllm.attention.backends.abstract import AttentionMetadata  # type: ignore
+    else:
+        from vllm.v1.attention.backend import AttentionMetadata  # type: ignore
     from vllm.distributed.kv_transfer.kv_connector.v1.metrics import (
         KVConnectorPromMetrics, KVConnectorStats, PromMetric, PromMetricT)
     from vllm.forward_context import ForwardContext
     from vllm.v1.core.kv_cache_manager import KVCacheBlocks
     from vllm.v1.kv_cache_interface import KVCacheConfig
     from vllm.v1.request import Request
+# isort: on
 
 
 class UCMConnectorV1(KVConnectorBase_V1):