alipay / alipay/PainlessInferenceAcceleration
modeling_qwen attention not use multi branch position ids & attention_mask
Open
- Dominant language
- Python
- Stars
- 370
- Forks
- 23
- PR merge metrics
- No merged PRs in 30d
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?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.