MegEngine / MegEngine/InferLLM

向量计算中使用CPU AVX指令,能否支持不使用AVX指令的版本

Open
#30 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
752
Forks
94
PR merge metrics
No merged PRs in 30d

Description

期待答复,谢谢

Contributor guide

No contributing guide indexed for this repository

Research direction

No source files, entry points, or tests are named. Start by locating the vector-computation code that uses CPU AVX instructions, then determine the intended non-AVX target and how inference behavior can be validated on it; done means a supported non-AVX version with appropriate verification.

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.