int8-flash-attention-fmha-quantization's People
Forkers
pommedeterresautee techthiyanes conceptofmind yangwang92 mard1no lin72h pppppm mfkiwl kleenelan fabianschuetze spacelabllm jimmieliu hanzz2007 hypertsengint8-flash-attention-fmha-quantization's Issues
Have you tested its speed?
I test it with batch_num=1, seq_len=128, head_num=5, head_dim=64. It shows "FMHA Inference took 75.82559204 ms, 17.97742325 GFlop/s, 0.01728598 GB/s INT8 average absolute deviation: 1.552685 %". But in torch model or TensorRT, it just takes 0.5ms per run.
LaTeX equation rendering broke down :(
[How-To] Quantize my own model in Tensorflow using this approach?
Does it support SM75?
Is it feasible to use SM75. There is no 'cp.async' for SM75.
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.