deepseek-ai / deepseek-ai/FlashMLA

Looking forward to additional configs in Flash Attenion 4

Open
#15 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
12.9k
Forks
1.2k
Avg merge
4h 20m
Merged PRs (30d)
2

Description

The Triton implementation of the [Flash Attention v2](https://tridao.me/publications/flash2/flash2.pdf) is currently a work in progress.

Would be nice to keep up with this implementation:
https://github.com/Dao-AILab/flash-attention

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by reading the repository's Triton implementation and comparing it with the linked Flash Attention repository. The issue names no files, tests, or specific configurations, so the required scope and completion criteria need to be clarified before implementation can begin.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.