EPISODE · Sep 29, 2025 · 7 MIN
DeepSeek-V3.2-Exp论文解读
from David的AI全景图
聊聊DeepSeek昨晚刚刚发布的最新模型DeepSeek-V3.2-Exp的公开论文。DeepSeek Sparse Attention(DSA)首次实现了细粒度稀疏注意力机制,在几乎不影响模型输出效果的前提下,实现了长文本训练和推理效率的大幅提升。来源:https://github.com/deepseek-ai/DeepSeek-V3.2-Exp/blob/main/DeepSeek_V3_2.pdf在小宇宙查看该单集文稿
Embed this episode
NOW PLAYING
DeepSeek-V3.2-Exp论文解读
0:00
7:13
1×
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
Frequently Asked Questions
How long is this episode of David的AI全景图?
This episode is 7 minutes long.
When was this David的AI全景图 episode published?
This episode was published on September 29, 2025.
Can I download this David的AI全景图 episode?
Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!