A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 02:15 UTC
Change default model to Qwen3-0.6B (#20335)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Tyler Michael Smith committed
Jul 14, 2025 at 12:54 UTC
559756214b770d0405939a05172804221c2f5677
1 file changed
+1
-1
vllm/config.py
+1
-1
@@ -226,7 +226,7 @@ ModelDType = Literal["auto", "half", "float16", "bfloat16", "float", "float32"]
226
class ModelConfig:
227
"""Configuration for the model."""
228
229
- model: str = "facebook/opt-125m"
229
+ model: str = "Qwen/Qwen3-0.6B"
230
"""Name or path of the Hugging Face model to use. It is also used as the
231
content for `model_name` tag in metrics output when `served_model_name` is
232
not specified."""