PaddlePaddle/flash-attention

PaddlePaddle/flash-attention

Description: Fast and memory-efficient exact attention

Language: Python

License: BSD-3-Clause

Stars: 21

Forks: 35

Open issues: 24

Created: 2023-02-02T13:04:25Z

Pushed: 2026-06-03T08:40:19Z

Default branch: main

Fork: yes

Parent repository: Dao-AILab/flash-attention

Archived: no

README:

FlashAttention

This repository provides the official implementation of FlashAttention and FlashAttention-2 from the following papers.

FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness Tri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra, Christopher Ré Paper: https://arxiv.org/abs/2205.14135 IEEE Spectrum article about our submission to the MLPerf 2.0 benchmark using FlashAttention. 

FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning Tri Dao

Paper: https://tridao.me/publications/flash2/flash2.pdf


Usage

We've been very happy to see FlashAttention being widely adopted in such a short time after its release. This page contains a partial list of places where FlashAttention is being used.

FlashAttention and FlashAttention-2 are free to use and modify (see LICENSE). Please cite and credit FlashAttention if you use it.

Installation and features

Requirements:

• CUDA 11.4 and above.
• PyTorch 1.12 and above.

We recommend the Pytorch container from Nvidia, which has all the required tools to install FlashAttention.

To install: 1. Make sure that PyTorch is installed. 2. Make sure that packaging is installed (pip install packaging) 3. Make sure that ninja is installed and that it works correctly (e.g. ninja --version then echo $? should return exit code 0). If not (sometimes ninja --version then echo $? returns a nonzero exit code), uninstall then reinstall ninja (pip uninstall -y ninja && pip install ninja). Without ninja, compiling can take a very long time (2h) since it does not use multiple CPU cores. With ninja compiling takes 3-5 minutes on a 64-core machine. 4. Then:

pip install flash-attn --no-build-isolation

Alternatively you can compile from source:

python setup.py install

If your machine has less than 96GB of RAM and lots of CPU cores, ninja might run too many parallel compilation jobs that could exhaust the amount of RAM. To limit the number of parallel compilation jobs, you can set the environment variable MAX_JOBS:

MAX_JOBS=4 pip install flash-attn --no-build-isolation

Interface: src/flash_attention_interface.py

FlashAttention-2 currently supports: 1. Ampere, Ada, or Hopper GPUs (e.g., A100, RTX 3090, RTX 4090, H100). Support for Turing GPUs (T4, RTX 2080) is coming soon, please use FlashAttention 1.x for Turing GPUs for now. 2. Datatype fp16 and bf16 (bf16 requires Ampere, Ada, or Hopper GPUs). 3. All head dimensions up to 256. Head dim > 192 backward requires A100/A800 or H100/H800.

How to use FlashAttention

The main functions implement scaled dot product attention (softmax(Q @ K^T * softmax_scale) @ V):

from flash_attn import flash_attn_qkvpacked_func, flash_attn_func

flash_attn_qkvpacked_func(qkv, dropout_p=0.0, softmax_scale=None, causal=False):
"""dropout_p should be set to 0.0 during evaluation
If Q, K, V are already stacked into 1 tensor, this function will be faster than
calling flash_attn_func on Q, K, V since the backward pass avoids explicit concatenation
of the gradients of Q, K, V.
Arguments:
qkv: (batch_size, seqlen, 3, nheads, headdim)
dropout_p: float. Dropout probability.
softmax_scale: float. The scaling of QK^T before applying softmax.
Default to 1 / sqrt(headdim).
causal: bool. Whether to apply causal attention mask (e.g., for auto-regressive modeling).
Return:
out: (batch_size, seqlen, nheads, headdim).
"""

flash_attn_func(q, k, v, dropout_p=0.0, softmax_scale=None, causal=False):
"""dropout_p should be set to 0.0 during evaluation
Supports multi-query and grouped-query attention (MQA/GQA) by passing in KV with fewer heads
than Q. Note that the number of heads in Q must be divisible by the number of heads in KV.
For example, if Q has 6 heads and K, V have 2 heads, head 0, 1, 2 of Q will attention to head
0 of K, V, and head 3, 4, 5 of Q will attention to head 1 of K, V.

Arguments:
q: (batch_size, seqlen, nheads, headdim)
k: (batch_size, seqlen, nheads_k, headdim)
v: (batch_size, seqlen, nheads_k, headdim)
dropout_p: float. Dropout probability.
softmax_scale: float. The scaling of QK^T before applying softmax.
Default to 1 / sqrt(headdim).
causal: bool. Whether to apply causal attention mask (e.g., for auto-regressive modeling).
Return:
out: (batch_size, seqlen, nheads, headdim).
"""

To see how these functions are used in a multi-head attention layer (which includes QKV projection, output projection), see the MHA implementation.

Upgrading from FlashAttention (1.x) to FlashAttention-2

These functions have been renamed:

• flash_attn_unpadded_func -> flash_attn_varlen_func
• flash_attn_unpadded_qkvpacked_func -> flash_attn_varlen_qkvpacked_func
• flash_attn_unpadded_kvpacked_func -> flash_attn_varlen_kvpacked_func

If the inputs have the same sequence lengths in the same batch, it is simpler and faster to use these functions:

flash_attn_qkvpacked_func(qkv, dropout_p=0.0, softmax_scale=None, causal=False)

flash_attn_func(q, k, v, dropout_p=0.0, softmax_scale=None, causal=False)

Performance

We present expected speedup (combined forward + backward pass) and memory savings from using FlashAttention against PyTorch standard attention, depending on sequence length, on different GPUs (speedup depends on memory bandwidth - we see more speedup on slower GPU memory).

We currently have benchmarks for these GPUs:

• [A100](#a100)
• [H100](#h100)

A100

We display FlashAttention speedup using these parameters:

• Head dimension 64 or 128, hidden dimension 2048 (i.e. either 32 or 16 heads).
• Sequence length 512, 1k, 2k, 4k, 8k, 16k.
• Batch size set to 16k / seqlen.

Speedup

![FlashAttention speedup on A100 80GB SXM5 with…