Upgrade to new vllm commit (#3719)

### 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

View File

@@ -24,6 +24,9 @@ import vllm.envs as envs_vllm
from vllm.logger import logger
from vllm.platforms import Platform, PlatformEnum
# todo: please remove it when solve cuda hard code in vllm
os.environ["VLLM_DISABLE_SHARED_EXPERTS_STREAM"] = "True"
from vllm_ascend.ascend_config import (check_ascend_config, get_ascend_config,
init_ascend_config)
from vllm_ascend.torchair.utils import (check_torchair_cache_exist,
@@ -142,7 +145,6 @@ class NPUPlatform(Platform):
if not model_config.is_multimodal_model and \
structured_outputs_config.backend == "auto" and \
not getattr(scheduler_config, "scheduler_delay_factor", 0) > 0 and \
not scheduler_config.send_delta_data and \
scheduler_config.policy == "fcfs":
ascend_scheduler_config.enabled = True
chunked_prefill_enabled_in_ascend_scheduler = getattr(