Update corresponding vllm commit ID to 12 29 (#5475)
### What this PR does / why we need it?
- Fixes vllm break:
1. [[BugFix] register quant scale tensors as buffer #31395]
(https://github.com/vllm-project/vllm/pull/31395)
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
5326c89803
---------
Signed-off-by: leo-pony <nengjunma@outlook.com>
This commit is contained in:
@@ -27,7 +27,7 @@ import torch_npu
|
||||
import vllm.envs as envs_vllm
|
||||
from torch_npu.op_plugin.atb._atb_ops import _register_atb_extensions
|
||||
from torch_npu.profiler import dynamic_profile as dp
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.config import VllmConfig, set_current_vllm_config
|
||||
from vllm.distributed import (ensure_model_parallel_initialized,
|
||||
init_distributed_environment)
|
||||
from vllm.distributed.ec_transfer import ensure_ec_transfer_initialized
|
||||
@@ -351,7 +351,8 @@ class NPUWorker(WorkerBase):
|
||||
else:
|
||||
from contextlib import nullcontext
|
||||
context = nullcontext() # type: ignore
|
||||
with context:
|
||||
|
||||
with context, set_current_vllm_config(self.vllm_config):
|
||||
self.model_runner.load_model()
|
||||
|
||||
def compile_or_warm_up_model(self) -> None:
|
||||
|
||||
Reference in New Issue
Block a user