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

[CI] rename Qwen2.5-0.5B-Instruct-W8A8 model (#1145)

Browse Source 
1. rename vllm-ascend/Qwen2.5-0.5B-Instruct-W8A8-new to
vllm-ascend/Qwen2.5-0.5B-Instruct-W8A8

Signed-off-by: 22dimensions <waitingwind@foxmail.com>
This commit is contained in:
22dimensions
2025-06-11 06:18:32 +08:00
committed by GitHub
parent 8dd686dfa2
commit 8b48daaa44
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/singlecard/test_offline_inference.py
View File

@@ -39,7 +39,7 @@ MODELS = [
MULTIMODALITY_MODELS = ["Qwen/Qwen2.5-VL-3B-Instruct"] MULTIMODALITY_MODELS = ["Qwen/Qwen2.5-VL-3B-Instruct"]
QUANTIZATION_MODELS = [ 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" os.environ["PYTORCH_NPU_ALLOC_CONF"] = "max_split_size_mb:256"