Open jihuishan opened 8 months ago
No response
Trying to finetune, yet running slow in training and inferring.
Just like Qwen-7B, could you support flash attention for Qwen-VL?
It perhaps costs some effort to implement.
The same Question
the same question
起始日期 | Start Date
No response
实现PR | Implementation PR
No response
相关Issues | Reference Issues
No response
摘要 | Summary
Trying to finetune, yet running slow in training and inferring.
基本示例 | Basic Example
Just like Qwen-7B, could you support flash attention for Qwen-VL?
缺陷 | Drawbacks
It perhaps costs some effort to implement.
未解决问题 | Unresolved questions
No response