JuliaGPU/CUDA.jl

cuDNN: Provide wrappers for the declarative API

Open

#2,266 opened on Feb 14, 2024

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Julia (1,408 stars) (274 forks)batch import
enhancementhelp wanted

Description

As part of cuDNN 9.0, the old imperative API has been deprecated, while moving towards a new, graph-based declarative API. That means that our wrappers will have to be rewritten. As I'm not familiar with machine learning / NNlib.jl (which I guess these wrappers would need to be compatible with), I'm hoping that people from the ML community could be able to help with this.

cc @ToucheSir @CarloLucibello @mcabbott @DhairyaLGandhi

Contributor guide

Tech stack
ccpp
Domain
machine learningapi
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
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.
mostly clear
Prerequisites
Knowledge of cuDNN declarative APIFamiliarity with Julia and CUDA.jlUnderstanding of NNlib.jl
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
15
Research direction
Review the cuDNN 9.0 declarative API documentation and the existing imperative wrappers in CUDA.jl. Understand the NNlib.jl interface requirements. Discuss with maintainers and the ML community to design the new wrapper API. Implement and test the wrappers.