From 8b48daaa44e11b26024a52705d3d3d4056eb57b6 Mon Sep 17 00:00:00 2001 From: 22dimensions Date: Wed, 11 Jun 2025 06:18:32 +0800 Subject: [PATCH] [CI] rename Qwen2.5-0.5B-Instruct-W8A8 model (#1145) 1. rename vllm-ascend/Qwen2.5-0.5B-Instruct-W8A8-new to vllm-ascend/Qwen2.5-0.5B-Instruct-W8A8 Signed-off-by: 22dimensions --- tests/singlecard/test_offline_inference.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/singlecard/test_offline_inference.py b/tests/singlecard/test_offline_inference.py index 5b58df7..de69612 100644 --- a/tests/singlecard/test_offline_inference.py +++ b/tests/singlecard/test_offline_inference.py @@ -39,7 +39,7 @@ MODELS = [ MULTIMODALITY_MODELS = ["Qwen/Qwen2.5-VL-3B-Instruct"] QUANTIZATION_MODELS = [ - "vllm-ascend/Qwen2.5-0.5B-Instruct-W8A8-new", + "vllm-ascend/Qwen2.5-0.5B-Instruct-W8A8", ] os.environ["PYTORCH_NPU_ALLOC_CONF"] = "max_split_size_mb:256"