hkproj / pytorch-llama-notes Goto Github PK
View Code? Open in Web Editor NEWNotes about LLaMA 2 model
Home Page: https://youtu.be/Mn_9W1nCFLo
pytorch-llama-notes's People
Contributors
Stargazers
Watchers
pytorch-llama-notes's Issues
Question regarding kv cache
hi,
first of all, thanks for the video and slides, very helpful! However, I do have a question regarding KV Cache:
in each layer, once attention is calculated, it then goes through RMS and FF operations, changes the input of the next layer, therefore the cached KV after the 1st layer won't be useful. I'm pretty sure I got it wrong but what I missed?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.