vllm.model_executor.models.qwen3
¶
Inference-only Qwen3 model compatible with HuggingFace weights.
Functions:
-
use_qwen2_attention–Make Qwen3 layers build Qwen2 attention: QKV bias and opt-in q/k-norm.
use_qwen2_attention(config)
¶
Make Qwen3 layers build Qwen2 attention: QKV bias and opt-in q/k-norm.