support deepseek quant & mix-parallel with graphmode (#585)

### What this PR does / why we need it?
1. support deepseek with w8a8 quant;
2. support deepseek with mix-parallel(multi-DP, EP+TP);
3. support deepseek with graphmode.
---------

Signed-off-by: wen-jie666 <wenjie39@huawei.com>
Signed-off-by: Yizhou Liu <liuyizhou5@h-partners.com>
Signed-off-by: libaokui <libaokui@huawei.com>
Signed-off-by: linfeng-yuan <1102311262@qq.com>
Co-authored-by: wen-jie666 <wenjie39@huawei.com>

vllm_ascend/utils.py

@@ -16,8 +16,6 @@
 # This file is a part of the vllm-ascend project.
 # Adapted from vllm-project/vllm/vllm/worker/worker.py
 #
-import os
-
 import torch
 import torch_npu  # noqa: F401
 from packaging.version import Version
@@ -25,8 +23,6 @@ from vllm.logger import logger
 
 import vllm_ascend.envs as envs
 
-VLLM_ENABLE_GRAPH_MODE = os.environ.get('VLLM_ENABLE_GRAPH_MODE', '0')
-
 
 def try_register_lib(lib_name: str, lib_info: str = ""):
     import importlib