EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Upgrade to new vllm commit (#3719)

Browse Source 
### What this PR does / why we need it?
Upgrade to new vllm commit:
c9461e05a4

- Fix many imports, caused by
https://github.com/vllm-project/vllm/pull/26908
- Fix import ```sha256```, caused by
https://github.com/vllm-project/vllm/pull/27169
- Remove ```SchedulerConfig.send_delta_data```, caused by
https://github.com/vllm-project/vllm/pull/27142
- Fix ```FusedMoE``` because of dual stream execution, caused by
https://github.com/vllm-project/vllm/pull/26440

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with new added/existing test.


- vLLM version: v0.11.0rc3
- vLLM main:
17c540a993

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: Icey <1790571317@qq.com>
Co-authored-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Icey
2025-10-25 15:36:32 +08:00
committed by GitHub
parent 226f832c0b
commit d9cdc65854
37 changed files with 229 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
vllm_ascend/spec_decode/mtp_proposer.py
View File

@@ -9,8 +9,8 @@ from vllm.config import (CUDAGraphMode, VllmConfig,
from vllm.forward_context import BatchDescriptor, get_forward_context
from vllm.model_executor.layers.attention_layer_base import AttentionLayerBase
from vllm.model_executor.model_loader import get_model_loader
from vllm.model_executor.model_loader.utils import (
process_weights_after_loading, set_default_torch_dtype)
from vllm.model_executor.model_loader.utils import \
process_weights_after_loading
from vllm.model_executor.models.deepseek_mtp import DeepSeekMTP
from vllm.v1.core.sched.output import SchedulerOutput
from vllm.v1.sample.metadata import SamplingMetadata
@@ -24,7 +24,13 @@ 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)
if vllm_version_is("0.11.0"):
from vllm.model_executor.model_loader.utils import set_default_torch_dtype
else:
from vllm.utils.torch_utils import set_default_torch_dtype
PADDING_SLOT_ID = -1