alipay / alipay/PainlessInferenceAcceleration
modeling_qwen attention not use multi branch position ids & attention_mask
Abierto
- Lenguaje dominante
- Python
- Estrellas
- 370
- Forks
- 23
- Métricas de merge de PR
- Sin PR fusionados en 30 d
Descripción
I reviewed the code of modeling_qwen.py, and I noticed that, within the lookahead process, the draft_ids matched from the TrieTree are such that the attention_mask and position ids associated with these draft_ids are not being utilized in the attention mechanism. This, I believe, might be an implementation error. Could you please point out where my understanding is incorrect?
Guía de contribución
No hay ninguna guía de contribución indexada para este repositorio
Evaluación
Este issue todavía no se ha evaluado.