EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[CI] upgrade vllm to 0.8.5 (#715)

Browse Source 
1. Upgrade vllm to 0.8.5
2. Drop 0.8.4 support
3. Keep doc to 0.8.4rc2 until we release 0.8.5

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-04-30 09:15:50 +08:00
committed by GitHub
parent 95e7aa4736
commit f8350569e6
20 changed files with 48 additions and 579 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm_ascend/worker/worker_v1.py
View File

@@ -29,6 +29,7 @@ from vllm.config import VllmConfig
from vllm.distributed import (ensure_model_parallel_initialized,
init_distributed_environment,
set_custom_all_reduce)
from vllm.distributed.kv_transfer import ensure_kv_transfer_initialized
from vllm.logger import logger
from vllm.model_executor import set_random_seed
from vllm.utils import STR_DTYPE_TO_TORCH_DTYPE
@@ -41,14 +42,9 @@ from vllm.v1.worker.worker_base import WorkerBase
from vllm_ascend.distributed.parallel_state import init_ascend_model_parallel
from vllm_ascend.platform import NPUPlatform
from vllm_ascend.utils import try_register_lib, vllm_version_is
from vllm_ascend.utils import try_register_lib
from vllm_ascend.worker.model_runner_v1 import NPUModelRunner
if vllm_version_is("0.8.4"):
from vllm.distributed import ensure_kv_transfer_initialized
else:
from vllm.distributed.kv_transfer import ensure_kv_transfer_initialized
class NPUWorker(WorkerBase):