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

[Test] Remove VLLM_USE_V1 in accuracy test (#1739)

Browse Source 
### What this PR does / why we need it?
Remove VLLM_USE_V1 in accuracy test

Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
zhangxinyuehfad
2025-07-11 15:29:11 +08:00
committed by GitHub
parent ee40d3d850
commit 1cd27da5fb
2 changed files with 4 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
benchmarks/scripts/run_accuracy.py
View File

@@ -168,7 +168,6 @@ def generate_md(model_name, tasks_list, args, datasets):
**Software Environment**: CANN: {args.cann_version}, PyTorch: {args.torch_version}, torch-npu: {args.torch_npu_version}
**Hardware Environment**: Atlas A2 Series
**Datasets**: {datasets}
**vLLM Engine**: V{args.vllm_use_v1}
**Parallel Mode**: {PARALLEL_MODE[model_name]}
**Execution Mode**: {EXECUTION_MODE[model_name]}
**Command**:
@@ -310,6 +309,5 @@ if __name__ == "__main__":
parser.add_argument("--cann_version", type=str, required=False)
parser.add_argument("--vllm_commit", type=str, required=False)
parser.add_argument("--vllm_ascend_commit", type=str, required=False)
parser.add_argument("--vllm_use_v1", type=str, required=False)
args = parser.parse_args()
main(args)