deepseek-ai / deepseek-ai/DeepSeek-V3.2-Exp
Whether DSA of prefill stage use MQA mode or MHA mode?
Open
- Dominant language
- Python
- Stars
- 1.7k
- Forks
- 190
- PR merge metrics
- No merged PRs in 30d
Description
The code of inference demo (https://github.com/deepseek-ai/DeepSeek-V3.2-Exp/blob/main/inference/model.py#L563) shows that DSA of prefill stage uses **MHA mode**. However, in the technique report, the author claims that DSA is instantiated based on **MQA mode**. And in FlashMLA repo, the DSA for prefill stage only supports MQA mode. Is it a bug in the inference demo?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.