[Test] Remove VLLM_USE_V1 in example and tests (#1733)

V1 is enabled by default, no need to set it by hand now. This PR remove
the useless setting in example and tests

- vLLM version: v0.9.2
- vLLM main:
9ad0a4588b

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

examples/offline_data_parallel.py

@@ -120,7 +120,6 @@ def main(
     trust_remote_code,
 ):
     # DP only support on V1 engine
-    os.environ["VLLM_USE_V1"] = "1"
     os.environ["VLLM_DP_RANK"] = str(global_dp_rank)
     os.environ["VLLM_DP_RANK_LOCAL"] = str(local_dp_rank)
     os.environ["VLLM_DP_SIZE"] = str(dp_size)

examples/offline_dualbatch_overlap_npu.py

@@ -5,7 +5,6 @@ from vllm import LLM, SamplingParams
 
 # enable dual-batch overlap for vllm ascend
 os.environ["VLLM_ASCEND_ENABLE_DBO"] = "1"
-os.environ["VLLM_USE_V1"] = "1"
 
 # Sample prompts.
 prompts = ["The president of the United States is"] * 41

examples/offline_inference_sleep_mode_npu.py

@@ -22,7 +22,6 @@ import torch
 from vllm import LLM, SamplingParams
 from vllm.utils import GiB_bytes
 
-os.environ["VLLM_USE_V1"] = "1"
 os.environ["VLLM_USE_MODELSCOPE"] = "True"
 os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
 

examples/run_dp_attention_etp16.sh

@@ -1,4 +1,3 @@
-export VLLM_USE_V1=1
 export TASK_QUEUE_ENABLE=1
 source /usr/local/Ascend/ascend-toolkit/set_env.sh
 source /usr/local/Ascend/nnal/atb/set_env.sh