Home/Inference & Serving/Star-Attention

Star-Attention

NVIDIA/Star-Attention

Efficient LLM Inference over Long Sequences

GitHub Website

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

34views this month

392 stars24 forksLast push Jun 25, 2025 Python Apache-2.0

Decision brief

Star-Attention specializes in long sequence inference of large language models using star-attention to maintain efficiency.

Good fit when

For applications requiring handling very large input sequences
When you need to enhance computational efficiency with star-attention mechanism

Avoid when

If your use case involves short sequence processing only
In scenarios where traditional attention mechanisms yield adequate results without performance loss

Observed Jul 15, 2026 · Source: enrich:decision_facts

Star-Attention alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Dormant (451d since push); As of Sep 20, 2026
Provenance: Not a fork · Organization account; As of Sep 20, 2026
Security (OSV): No lockfile; As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Backing

Company context for Nvidia. Display-only - separate from trust and ranking.

Company: NVIDIA Corporation·GitHub org profile·Jul 11, 2026
Employees: 11,528·Wikidata (P1128 employees)·Jul 11, 2026
Commercial model: Pure OSS·GitHub org profile (public repos)·Jul 11, 2026

Install

pip install Star-Attention

PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

peft

State-of-the-art Parameter-Efficient Fine-Tuning

22k★

bitsandbytes

Large language model quantization toolkit for PyTorch.

8.5k★

Liger-Kernel

Efficient Triton Kernels for LLM Training

6.6k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

A Python project for efficient inference of large language models with long sequences using star-attention mechanisms.

Capability facts

Languages: python
Source: github.language · Sep 20, 2026

Graph entities

Nvidiacompany

README

Star Attention: Efficient LLM Inference over Long Sequences This repository contains code for the paper Star Attention: Efficient LLM Inference over Long Sequences. Star Attention is a novel block sparse attention mechanism designed to enable efficient inference on long sequences...

For agents

This page has a .md twin and JSON over the API.

/tools/nvidia-star-attention.md GET /api/graphcanon/tools/nvidia-star-attention GET /api/graphcanon/graph?tool=nvidia-star-attention