[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>
2026-02-02 15:57:55 +08:00
parent d53510b26d
commit eeedf7c503
32 changed files with 81 additions and 108 deletions
--- a/vllm_ascend/ascend_forward_context.py
+++ b/vllm_ascend/ascend_forward_context.py
@@ -19,7 +19,6 @@ from vllm_ascend.utils import (
    is_drafter_moe_model,
    is_moe_model,
    speculative_enable_dispatch_gmm_combine_decode,
-    vllm_version_is,
 )


@@ -57,11 +56,9 @@ def set_ascend_forward_context(
        "num_tokens_across_dp": num_tokens_across_dp,
        "cudagraph_runtime_mode": aclgraph_runtime_mode,
        "batch_descriptor": batch_descriptor,
+        "skip_compiled": skip_compiled,
    }

-    if not vllm_version_is("0.14.1"):
-        forward_context_kwargs["skip_compiled"] = skip_compiled
-
    with set_forward_context(**forward_context_kwargs):
        forward_context = get_forward_context()

--- a/vllm_ascend/attention/attention_v1.py
+++ b/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()
--- a/vllm_ascend/attention/mla_v1.py
+++ b/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
--- a/vllm_ascend/attention/sfa_v1.py
+++ b/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
--- a/vllm_ascend/ops/fused_moe/fused_moe.py
+++ b/vllm_ascend/ops/fused_moe/fused_moe.py
@@ -512,6 +512,14 @@ class AscendSharedFusedMoE(SharedFusedMoE, AscendFusedMoE):
        hidden_states: torch.Tensor,
        router_logits: torch.Tensor,
    ) -> tuple[torch.Tensor, torch.Tensor]:
+        if self._shared_experts is None:
+            fused_out = AscendFusedMoE.forward(
+                self,
+                hidden_states=hidden_states,
+                router_logits=router_logits,
+            )
+            shared_out = None
+            return shared_out, fused_out
        shared_out, fused_out = AscendFusedMoE.forward(
            self,
            hidden_states=hidden_states,
@@ -571,6 +579,9 @@ class AscendSharedFusedMoE(SharedFusedMoE, AscendFusedMoE):
        )
        routed_out = fused_moe_results.routed_out

+        if self._shared_experts is None:
+            return routed_out
+
        if self.multistream_overlap_gate:
            fc3_context = get_flash_common3_context()
            assert fc3_context is not None
--- a/vllm_ascend/ops/mm_encoder_attention.py
+++ b/vllm_ascend/ops/mm_encoder_attention.py
@@ -38,7 +38,6 @@ class AscendMMEncoderAttention(MMEncoderAttention):
        scale: float | None = None,
        num_kv_heads: int | None = None,
        prefix: str = "",
-        multimodal_config: MultiModalConfig | None = None,
    ) -> None:
        """
        Args:
@@ -56,7 +55,6 @@ class AscendMMEncoderAttention(MMEncoderAttention):
            scale=scale,
            num_kv_heads=num_kv_heads,
            prefix=prefix,
-            multimodal_config=multimodal_config,
        )

    def reshape_qkv_to_3d(
--- a/vllm_ascend/patch/platform/init.py
+++ b/vllm_ascend/patch/platform/init.py
@@ -25,5 +25,5 @@ from vllm_ascend.utils import vllm_version_is
 if os.getenv("DYNAMIC_EPLB", "false").lower() in ("true", "1") or os.getenv("EXPERT_MAP_RECORD", "false") == "true":
    import vllm_ascend.patch.platform.patch_multiproc_executor  # noqa

-if envs.VLLM_ASCEND_BALANCE_SCHEDULING and vllm_version_is("0.14.0"):
+if envs.VLLM_ASCEND_BALANCE_SCHEDULING and vllm_version_is("0.15.0"):
    import vllm_ascend.patch.platform.patch_balance_schedule  # noqa
--- a/vllm_ascend/patch/platform/patch_multiproc_executor.py
+++ b/vllm_ascend/patch/platform/patch_multiproc_executor.py
@@ -19,8 +19,6 @@ from vllm.v1.executor.multiproc_executor import (
    set_multiprocessing_worker_envs,
 )

-from vllm_ascend.utils import vllm_version_is
-

 class AscendMultiprocExecutor(MultiprocExecutor):
    def _init_executor(self) -> None:
@@ -177,9 +175,8 @@ class AscendWorkerProc(WorkerProc):
            "ready_pipe": (reader, writer),
            "death_pipe": death_reader,
            "shared_worker_lock": shared_worker_lock,
+            "is_driver_worker": is_driver_worker,
        }
-        if not vllm_version_is("0.14.1"):
-            process_kwargs["is_driver_worker"] = is_driver_worker
        # Run EngineCore busy loop in background process.
        proc = context.Process(
            target=WorkerProc.worker_main,
--- a/vllm_ascend/spec_decode/eagle_proposer.py
+++ b/vllm_ascend/spec_decode/eagle_proposer.py
@@ -41,7 +41,7 @@ from vllm_ascend.ops.rotary_embedding import update_cos_sin
 from vllm_ascend.ops.triton.spec_decode.utils import \
    prepare_inputs_padded_kernel
 from vllm_ascend.ops.triton.triton_utils import get_vectorcore_num
-from vllm_ascend.utils import enable_sp, shared_expert_dp_enabled, vllm_version_is
+from vllm_ascend.utils import enable_sp, shared_expert_dp_enabled

 # Currently we will fix block size to a small one since `num_reqs` can't be too large
 _PREPARE_INPUTS_BLOCK_SIZE = 4
@@ -456,11 +456,8 @@ class EagleProposer(VllmEagleProposer):
        self.input_ids[last_token_indices] = next_token_ids
        if self.use_cuda_graph and \
            num_tokens <= self.runner.cudagraph_batch_sizes[-1]:
-            if vllm_version_is('0.14.1'):
-                num_input_tokens = self.vllm_config.pad_for_cudagraph(num_tokens)
-            else:
-                num_input_tokens = self.runner.cudagraph_dispatcher._bs_to_padded_graph_size[
-                    num_tokens]
+            num_input_tokens = self.runner.cudagraph_dispatcher._bs_to_padded_graph_size[
+                num_tokens]
        else:
            num_input_tokens = num_tokens

--- a/vllm_ascend/spec_decode/mtp_proposer.py
+++ b/vllm_ascend/spec_decode/mtp_proposer.py
@@ -18,7 +18,7 @@ from vllm_ascend.attention.utils import AscendCommonAttentionMetadata
 from vllm_ascend.compilation.acl_graph import ACLGraphWrapper
 from vllm_ascend.ops.rotary_embedding import get_cos_and_sin_mla
 from vllm_ascend.spec_decode.eagle_proposer import EagleProposer
-from vllm_ascend.utils import lmhead_tp_enable, vllm_version_is
+from vllm_ascend.utils import lmhead_tp_enable


 class MtpProposer(EagleProposer):
@@ -245,12 +245,8 @@ class MtpProposer(EagleProposer):
        # Note(qcs): We may need to refactor these check logics.
        if self.use_cuda_graph and num_scheduled_tokens <= self.runner.cudagraph_batch_sizes[
                -1]:
-            if vllm_version_is('0.14.1'):
-                num_input_tokens = self.vllm_config.pad_for_cudagraph(
-                    num_scheduled_tokens)
-            else:
-                num_input_tokens = self.runner.cudagraph_dispatcher._bs_to_padded_graph_size[
-                    num_scheduled_tokens]
+            num_input_tokens = self.runner.cudagraph_dispatcher._bs_to_padded_graph_size[
+                num_scheduled_tokens]
        else:
            # Eager mode, no padding needed
            num_input_tokens = num_tokens
--- a/vllm_ascend/worker/v2/aclgraph_utils.py
+++ b/vllm_ascend/worker/v2/aclgraph_utils.py
@@ -28,14 +28,11 @@ from vllm.v1.worker.gpu.cudagraph_utils import CudaGraphManager
 from vllm.v1.worker.gpu.cudagraph_utils import \
    prepare_inputs_to_capture as prepare_inputs_to_capture_gpu
 from vllm.v1.worker.gpu.input_batch import InputBuffers
+from vllm.v1.attention.backend import AttentionMetadataBuilder

 from vllm_ascend.worker.v2.utils import torch_cuda_wrapper
-from vllm_ascend.utils import vllm_version_is

-if vllm_version_is('0.14.1'):
-    from vllm.v1.attention.backends.utils import AttentionMetadataBuilder
-else:
-    from vllm.v1.attention.backend import AttentionMetadataBuilder
+


 class AclGraphManager(CudaGraphManager):
--- a/vllm_ascend/worker/v2/attn_utils.py
+++ b/vllm_ascend/worker/v2/attn_utils.py
@@ -24,17 +24,13 @@ import numpy as np
 import torch
 from vllm.config import VllmConfig
 from vllm.v1.kv_cache_interface import EncoderOnlyAttentionSpec, KVCacheConfig
+from vllm.v1.attention.backend import AttentionMetadataBuilder

 from vllm_ascend.attention.attention_mask import AttentionMaskBuilder
 from vllm_ascend.attention.attention_v1 import AscendAttentionState
 from vllm_ascend.attention.utils import (AscendCommonAttentionMetadata,
                                         AscendPrefillContextParallelMetadata)
-from vllm_ascend.utils import vllm_version_is

-if vllm_version_is('0.14.1'):
-    from vllm.v1.attention.backends.utils import AttentionMetadataBuilder
-else:
-    from vllm.v1.attention.backend import AttentionMetadataBuilder

 _ATTENTION_MASK_BUILDER = None