[CI] Upgrade vllm to newest commit (#3182)

### What this PR does / why we need it?
Upgrade vLLM to newest commit

- Fix the aclgraph doesn't work problem, caused by
24fab45d96
- Fix PoolerOutput import error, caused by
755ed7b05b
- Fix the aclgraph weight load error to keep the same with torchair fix.
4492e3a554

### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
All test should pass


- vLLM version: v0.10.2
- vLLM main:
52d0cb8458

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-09-26 06:18:15 +08:00
committed by GitHub
parent 0794f64a18
commit 2930e4a6bd
9 changed files with 49 additions and 53 deletions

View File

@@ -28,20 +28,6 @@ from vllm_ascend.worker.worker_v1 import NPUWorker
class NPUTorchairWorker(NPUWorker):
"""Torchair worker bases on NPUWorker. Only torchair specified code should be added in this class."""
def __init__(self,
vllm_config,
local_rank,
rank,
distributed_init_method,
is_driver_worker=False,
**kwargs):
super().__init__(vllm_config, local_rank, rank,
distributed_init_method, is_driver_worker, **kwargs)
from vllm.model_executor.layers.linear import \
WEIGHT_LOADER_V2_SUPPORTED
if "UnquantizedLinearMethod" in WEIGHT_LOADER_V2_SUPPORTED:
WEIGHT_LOADER_V2_SUPPORTED.remove("UnquantizedLinearMethod")
def determine_available_memory(self) -> int:
"""Override determine_available_memory to use cached torchair kv_cache_bytes."""