Git Product home page Git Product logo

Comments (2)

tonylins avatar tonylins commented on June 21, 2024 2

Hi @codertimo , usually W8A8 (SmoothQuant) is better for compute-bounded scenarios (e.g., large batch size, targeting large throughput), and W4A16 (AWQ) is better for memory-bounded scenarios (smaller batch size, lower latency). Let me know if you have more questions.

from llm-awq.

casper-hansen avatar casper-hansen commented on June 21, 2024 1

Question

We are very interested in two post-training quantization papers from han lab!

SmoothQuant use W8A8 for efficient GPU computation. AWQ uses W4/3A16 for lower memory requirements and higher memory throughput.

But which one is faster in actual production? If you have any data about this, could you share it with us?

W4A16 is the fastest. I believe this is discussed in the paper, something along the lines of “weights make up the majority of delay”. Most layers in transformers are linear layers, so naturally you will see a large benefit from quantizing them.

I don’t have benchmarks to compare against SmoothQuant as it seems AWQ is preferred by the authors due to usability and speed with TinyChat.

from llm-awq.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.