microsoft/MInference

A Python library that speeds up inference for large language models by up to 10x with dynamic sparse attention

Python
AI & Machine Learning
LLM Frameworks
MIT

1.2K

Stars

75

Forks

May 22, 2024

Created

Sep 30, 2025

Last Updated

Project Analytics

Stars Growth (1 Month)

+7

+0.6% change

Avg Daily Growth (1 Month)

+0.3

stars per day

Fork/Star Ratio (All Time)

6.3%

Normal engagement

Lifetime Growth

1.8

stars/day over 654 days

Stars Over Time

Forks Over Time

Open Issues Over Time

Pull Requests Over Time

Commits Over Time

AI-Generated Tags

large-language-models
inference-optimization
sparse-attention
performance-optimization
cli-tool

Comments (0)

Sign in to leave a comment or vote

Sign In

No comments yet. Be the first to comment!

Stay in the loop

Get weekly updates on trending AI coding tools and projects.