Tencent/TurboTransformers

Refactor MultiheadAttention and other Layers

Open

#140 opened on Jul 22, 2020

View on GitHub
 (0 comments) (0 reactions) (0 assignees)C++ (206 forks)github user discovery
enhancementhelp wanted

Repository metrics

Stars
 (1,546 stars)
PR merge metrics
 (PR metrics pending)

Description

Now the logic inside MultiheadAttention Layer is too complex for development. Moreover, some bugs exist in intermediate management. It is the first priority to rewrite these codes to make others easily understand what Turbo is doing.

Contributor guide

Research direction
Examine the current MultiheadAttention implementation, identify redundant or buggy code paths, and refactor to a simpler structure.
Tech stack
None
Domain
backend
Issue type
Refactor
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.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
C++Transformer Models
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
45