[Main2Main][Deps][Misc] Upgrade vLLM to v0.15.0 (#6470)

### What this PR does / why we need it?
This PR upgrades the vLLM dependency from `v0.14.1` to `v0.15.0`. This
involves:
- Updating the `VLLM_TAG` in all `Dockerfile`.
- Updating the vLLM version in `docs/source/conf.py`.
- Removing conditional code paths specific to `v0.14.1` across the
codebase, which simplifies maintenance.
- Fix `TypeError: MMEncoderAttention.__init__() got an unexpected
keyword argument 'multimodal_config'` due to
https://github.com/vllm-project/vllm/pull/31972.
- Fix `_shared_experts: 'NoneType' object is not callable` due to
https://github.com/vllm-project/vllm/pull/32082 by
https://github.com/vllm-project/vllm-ascend/pull/6335.
- Fix `ReshapeAndCacheOperation setup failed!` due to
https://github.com/vllm-project/vllm/pull/25954 by overriding attention
metadata slots.

This upgrade is necessary to keep the project aligned with the latest
features, bug fixes, and API changes in the vLLM project.

### Does this PR introduce _any_ user-facing change?
No, this is an internal dependency update and does not introduce any
user-facing changes.

### How was this patch tested?
CI is expected to pass with these changes, ensuring that all existing
tests are successful with the new vLLM version.

- vLLM version: v0.14.1
- vLLM main:
dc917cceb8


co-authored-by: shen-shanshan <467638484@qq.com>

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

vllm_ascend/attention/attention_v1.py

@@ -278,6 +278,8 @@ class AscendAttentionMetadataBuilder(AttentionMetadataBuilder[AscendMetadata]):
         seq_lens = common_attn_metadata.seq_lens_cpu[:num_reqs]
 
         slot_mapping = common_attn_metadata.slot_mapping[:num_actual_tokens]
+        # this slot_mapping override doesn't work since vllm will override it again. We should fix it vllm.
+        # see: https://github.com/vllm-project/vllm/blob/ce88756b967c2c5006746a424c15dd59a284ed8c/vllm/model_executor/layers/attention/cross_attention.py#L117
         if isinstance(self.kv_cache_spec, CrossAttentionSpec):
             seq_lens = common_attn_metadata.seq_lens
             slot_mapping = common_attn_metadata.slot_mapping.to(torch.int32)
@@ -873,7 +875,9 @@ class AscendAttentionBackendImpl(AttentionImpl):
                 value=value[: attn_metadata.num_actual_tokens] if not encoder_decoder else value,
                 key_cache=self.key_cache,
                 value_cache=self.value_cache,
-                slot_mapping=slots[: attn_metadata.num_actual_tokens] if not encoder_decoder else slots,
+                # quick fix to make sure slots is int32 for cross attention case.
+                # see: https://github.com/vllm-project/vllm/blob/ce88756b967c2c5006746a424c15dd59a284ed8c/vllm/model_executor/layers/attention/cross_attention.py#L117
+                slot_mapping=slots[: attn_metadata.num_actual_tokens] if not encoder_decoder else slots.to(torch.int32),
             )
             if self.is_kv_producer:
                 attn_metadata.reshape_cache_event.record()

vllm_ascend/attention/mla_v1.py

@@ -8,6 +8,7 @@ import vllm.envs as envs_vllm
 from vllm.config import VllmConfig, get_current_vllm_config
 from vllm.forward_context import ForwardContext, get_forward_context
 from vllm.logger import logger
+from vllm.model_executor.layers.attention.mla_attention import MLACommonMetadataBuilder
 from vllm.model_executor.layers.linear import UnquantizedLinearMethod
 from vllm.utils.math_utils import cdiv, round_down
 from vllm.v1.attention.backend import AttentionBackend, AttentionCGSupport, MLAAttentionImpl  # type: ignore
@@ -44,18 +45,12 @@ from vllm_ascend.ops.layer_shard_linear import (
 from vllm_ascend.ops.rotary_embedding import get_cos_and_sin_mla
 from vllm_ascend.ops.weight_prefetch import maybe_npu_prefetch
 from vllm_ascend.quantization.methods import AscendW8A8LinearMethod
-from vllm_ascend.utils import ACL_FORMAT_FRACTAL_ND, maybe_trans_nz, vllm_version_is, weak_ref_tensors
+from vllm_ascend.utils import ACL_FORMAT_FRACTAL_ND, maybe_trans_nz, weak_ref_tensors
 from vllm_ascend.worker.npu_input_batch import NPUInputBatch
 
 if TYPE_CHECKING:
     from vllm.v1.core.sched.output import SchedulerOutput
 
-# isort: off
-if vllm_version_is("0.14.1"):
-    from vllm.v1.attention.backends.mla.common import MLACommonMetadataBuilder  # type: ignore
-else:
-    from vllm.model_executor.layers.attention.mla_attention import MLACommonMetadataBuilder
-# isort: on
 
 MAX_O_PROJ_PREFETCH_SIZE = 16 * 1024 * 1024
 BUILD_METADATA_STEP_PREFILL = 0

vllm_ascend/attention/sfa_v1.py

@@ -9,6 +9,7 @@ from vllm.config import 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
 from vllm.logger import logger
+from vllm.model_executor.layers.attention.mla_attention import MLACommonMetadataBuilder
 from vllm.model_executor.layers.linear import UnquantizedLinearMethod
 from vllm.triton_utils import HAS_TRITON
 from vllm.v1.attention.backend import AttentionBackend, AttentionCGSupport, MLAAttentionImpl  # type: ignore
@@ -45,17 +46,11 @@ from vllm_ascend.utils import (
     enable_dsa_cp,
     enable_dsa_cp_with_layer_shard,
     maybe_trans_nz,
-    vllm_version_is,
 )
 from vllm_ascend.worker.npu_input_batch import NPUInputBatch
 
 if TYPE_CHECKING:
     from vllm.v1.core.sched.output import SchedulerOutput
-if vllm_version_is("0.14.1"):
-    from vllm.v1.attention.backends.mla.common import MLACommonMetadataBuilder  # type: ignore
-else:
-    from vllm.model_executor.layers.attention.mla_attention import MLACommonMetadataBuilder
-# isort: on
 
 # token count limits within bmm_transpose operator
 BMM_TRANS_MAX_SUPPORTED_TOKENS = 1024