We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
https://medium.com/@zaiinn440/mha-vs-mqa-vs-gqa-vs-mla-c6cf8285bbec
The text was updated successfully, but these errors were encountered:
DeepSeekで使われているMulti Head Latent Attention(MLA)ってなんだ?と思い読んだ。端的に言うと、GQAやMQAは、KVのヘッドをそもそも減らしてKV Cacheを抑えよう、という手法だったが、MLAはKVを低ランクなベクトルに圧縮して保持し、使う時に復元するといった操作をすることで、MHAのパフォーマンスを落とすことなく(むしろ上がるらしい?)、利用するKV Cacheで利用するメモリを大幅に減らせるという手法らしい。
Sorry, something went wrong.
MQA, GQAの概要については上記参照のこと。
No branches or pull requests
https://medium.com/@zaiinn440/mha-vs-mqa-vs-gqa-vs-mla-c6cf8285bbec
The text was updated successfully, but these errors were encountered: