[CI] Upgrade vLLM to 20250919 (6d8246aa) and fix some broken issue (#2907)

### What this PR does / why we need it?
1. This pr bump vllm commit to
6d8246aaff
2. fix upstream changes https://github.com/vllm-project/vllm/pull/24548
abort multi-modal kwargs, make vllm main and `v0.10.2` both adaptable
3. fix metadata_builder changes introduced by
https://github.com/vllm-project/vllm/pull/23693
4. fix `structured_outputs_config` changes introduced by
https://github.com/vllm-project/vllm/pull/22772
5. fix `moe_config` changes introduced by
https://github.com/vllm-project/vllm/pull/22537

Co-authored-by:  MengqingCao <cmq0113@163.com>
Co-authored-by:  Yikun Jiang <yikunkero@gmail.com>


- vLLM version: v0.10.2
- vLLM main:
c60e6137f0

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Li Wang
2025-09-20 17:37:57 +08:00
committed by GitHub
parent 53ecd89e8f
commit 12bcbd02bb
14 changed files with 359 additions and 143 deletions

View File

@@ -24,7 +24,8 @@ from vllm_ascend.torchair.models.torchair_deepseek_mtp import \
TorchairDeepSeekMTP
from vllm_ascend.torchair.utils import (TORCHAIR_CACHE_DIR,
TorchairCommonAttentionMetadata)
from vllm_ascend.utils import ProfileExecuteDuration, lmhead_tp_enable
from vllm_ascend.utils import (ProfileExecuteDuration, lmhead_tp_enable,
vllm_version_is)
PADDING_SLOT_ID = -1
@@ -395,7 +396,10 @@ class MtpProposer(Proposer):
seq_lens=None)
if not self.torchair_graph_enabled:
builder = self.runner.attn_groups[0][0].metadata_builder
if vllm_version_is("0.10.2"):
builder = self.runner.attn_groups[0][0].metadata_builder
else:
builder = self.runner.attn_groups[0][0].get_metadata_builder()
attn_metadata_mtp = builder.build(0, common_attn_metadata,
self.runner.get_model())