---
id: flash-attn-4
version: "4.0.0b26"
license: BSD 3-Clause License
license_treatment: permissive
maintenance: active
---

# flash-attn-4 — Flash Attention CUTE (CUDA Template Engine) implementation

License: permissive · Maintenance: active · Downloads: 2.0M/mo

## What it is and what it does

flash-attn-4 is a specialized GPU kernel library that reimplements the attention operation—a core component of transformer neural networks—using CuTeDSL for modern NVIDIA Hopper and Blackwell architectures. It trades general-purpose compatibility for speed and memory efficiency on these specific GPUs by fusing multiple attention computation steps into a single kernel, reducing memory bandwidth and improving cache locality.

The package is designed for researchers and practitioners building or fine-tuning large language models and other transformer-based systems where attention computation dominates runtime. It provides two main entry points: flash_attn_func for standard attention and flash_attn_varlen_func for variable-length sequences. Installation requires torch, nvidia-cutlass-dsl, and a compatible CUDA version; the package is in active development (alpha status) and updated frequently.

Use it for:

- Accelerate training or inference of large language models on Hopper/Blackwell GPUs by replacing standard attention with optimized kernels.
- Reduce memory consumption during transformer model training by fusing attention operations into a single GPU kernel.
- Implement causal attention for autoregressive language generation with lower latency.
- Handle variable-length sequences efficiently in batched transformer inference without padding overhead.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

GPU-accelerated attention mechanism implementation using CuTeDSL for Hopper and Blackwell GPUs, optimizing the core computational bottleneck in transformer models.

Yes, if you are training or running transformer models on Hopper or Blackwell GPUs and want lower latency and memory usage. The package is actively maintained, has no known vulnerabilities, and uses a permissive license. However, it is in alpha status and only useful for specific GPU hardware; it will not benefit users on other GPU architectures or CPU-only setups.

## Install

pip install flash-attn-4
uv add flash-attn-4
poetry add flash-attn-4

## Installing flash-attn-4

Before you install: Installation is straightforward with low friction. The package is actively maintained with a recent release (2 days old) and high repository engagement (24706 stars). Requires torch and NVIDIA GPU libraries as runtime dependencies.

License in practice: BSD 3-Clause License is permissive, allowing commercial and private use with minimal restrictions beyond attribution and liability disclaimers.

Quickstart:

pip install flash-attn-4
# or for CUDA 13:
# pip install "flash-attn-4[cu13]"

from flash_attn.cute import flash_attn_func
out = flash_attn_func(q, k, v, causal=True)

Requires an NVIDIA Hopper or Blackwell GPU and corresponding CUDA toolkit; torch must be installed and configured for your CUDA version.

Verify before relying:

- Performance benchmarks compared to standard PyTorch attention or other implementations.
- Supported tensor shapes, dtypes, and edge cases for q, k, v inputs.
- Memory overhead and actual speedup on different model sizes and batch configurations.
- Stability and numerical accuracy guarantees relative to standard attention.

## Package facts

- License: BSD 3-Clause License (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 2.0M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

gpu accelerated attention mechanism, hopper blackwell gpu optimization, transformer attention kernel, cuda attention optimization, efficient attention computation, gpu-kernels, transformer-optimization, cuda

[View on SkillFed](https://skillfed.io/packages/flash-attn-4) · [View on PyPI](https://pypi.org/project/flash-attn-4/)