Comments (5)
@pommedeterresautee Est ce qu'on va tester (moi, Jonathan et Gaetan) sur le même type de machine a10g ? (pour moi, on a vu que le RTX20 ça marche pas trés bien avec triton)
from kernl.
Oui, @gaetansnl va mettre en place un killer d'instance pour éviter une erreur d'extinction mais l'esprit est de tester dans le cloud
from kernl.
en fait, mon idée c'était qu'il vaut mieux tester avec différents types de machine sinon on va se retrouver à faire le même test avec le même code et la même machine.
from kernl.
Sur le cloud on a accès à deux générations de gpu, l'ajout de 2080 ou 3090 est un vrai plus, cependant peut être pas essentiel. Ceci étant on va pas étendre Triton a des architectures anciennes de gpu pour utilisateurs non pro si cela n'est pas supporté de base.
Par exemple dans le calcul d'une double gemm on a une grosse contrainte sur la quantité de shared memory disponible (un axe de deux des matrices soit entièrement rentrer dans la shared memory)
from kernl.
done through #56
from kernl.
Related Issues (20)
- Review the doc so that it displays correctly on the site ?
- Installation problem HOT 7
- feature: non verbose CI HOT 1
- bug: tests failing at nvidia-driver-530
- feature: using TorchBench to test the coverage HOT 2
- [FRONT] Upgrade kernl's M4M configuration with the Insiders version.
- bug: Trying to run T5 tutorial and getting `free(): invalid pointer` error. HOT 1
- bug: How to save the optimized model to file? HOT 3
- bug: Triton 2.0 makes attention kernel crash HOT 1
- bug: Llama model optimization failing HOT 4
- proposal: Write GEMM (matrice mulitplication) triton optimization animation
- bug: Llama reproduce error with kernl HOT 1
- bug: does kernl support pipeline parallel?
- bug: Bart speedup only 1.6x
- bug: start_position support for the fused attention kernel
- bug: Torch.dynamo is not working on H100 due to obsolete triton & pytorch
- bug: Experimental/Whisper notebook (speedup.ipynb) is not working
- bug: optimize_model() fails on HF's GPT2 with "RuntimeError: CUDA error: operation not permitted when stream is capturing" HOT 4
- Confuse about block_delta
- bug: Fails running dynamic shapes
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.
from kernl.