triton-lang/triton

Making fused attention work with GPUs other than A100

Open

#616 opened on Aug 9, 2022

View on GitHubContributor guide
 (7 comments) (0 reactions) (0 assignees)MLIR (3,136 forks)github user discovery
help wanted

Repository metrics

Stars
 (19,995 stars)
PR merge metrics
 (Avg merge 2d 18h) (185 merged PRs in 30d)

Description

I am curious why does the fused attention code only with A100? Is there a way to make it work on other GPUs such as Quadro GP100?

Contributor guide

Research direction
Investigate the fused attention kernel in the Triton codebase to identify GPU architecture specific code (e.g., sm 80). Test on target GPU and report errors. Check Triton's documentation on GPU support and look for any existing discussions about GPU compatibility.
Tech stack
python
Domain
backendperformance
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
Basic GPU programming conceptsFamiliarity with Triton
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40