[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

@@ -116,6 +116,12 @@ class NPUWorker(WorkerBase):
# Buffers saved before sleep
self._sleep_saved_buffers: dict[str, torch.Tensor] = {}
# FixMe: this is a patch to fix the issue cause by https://github.com/vllm-project/vllm/commit/de94289a98d7ec52a5ef02719e01a1db8b505170
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 sleep(self, level: int = 1) -> None:
if not sleep_mode_enabled():
raise ValueError(