[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 by24fab45d96- Fix PoolerOutput import error, caused by755ed7b05b- 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:
@@ -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(
|
||||
|
||||
Reference in New Issue
Block a user