biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Change default model to Qwen3-0.6B (#20335)

Browse Source 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Tyler Michael Smith
2025-07-14 12:54:52 -04:00
committed by GitHub
parent 6d0cf239c6
commit 559756214b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/config.py
View File

@@ -226,7 +226,7 @@ ModelDType = Literal["auto", "half", "float16", "bfloat16", "float", "float32"]
class ModelConfig: class ModelConfig:
"""Configuration for the model.""" """Configuration for the model."""
model: str = "facebook/opt-125m" model: str = "Qwen/Qwen3-0.6B"
"""Name or path of the Hugging Face model to use. It is also used as the """Name or path of the Hugging Face model to use. It is also used as the
content for `model_name` tag in metrics output when `served_model_name` is content for `model_name` tag in metrics output when `served_model_name` is
not specified.""" not specified."""