alipay / alipay/PainlessInferenceAcceleration
modeling_qwen attention not use multi branch position ids & attention_mask
Ouverte
- Langage dominant
- Python
- Étoiles
- 370
- Forks
- 23
- Métriques de merge des PR
- Aucune PR mergée en 30 j
Description
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?
Guide de contribution
Aucun guide de contribution indexé pour ce dépôt
Évaluation
Cette issue n'a pas encore été évaluée.