huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update flash_attention.md

Browse Source
This commit is contained in:
Merve Noyan 2023-08-22 21:43:52 +03:00 committed by GitHub
parent 172d262adf
commit 7037d0259f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
docs/source/conceptual/flash_attention.md
View File

@ -1,7 +1,12 @@
# Flash Attention
Scaling the transformer architecture is heavily bottlenecked by the self-attention mechanism, which has quadratic time and memory complexity. Recent developments in accelerator hardware mainly focus on enhancing compute capacities and not memory and transferring data between hardware. This results in attention operation having a memory bottleneck, also called memory-bound. **Flash Attention** is an attention algorithm used to reduce this problem and scale transformer-based models more efficiently, enabling faster training and inference.
In the standard attention implementation, the cost of loading and writing keys, queries, and values from High Bandwidth Memory (HBM) is high. It loads key, query, and value from HBM to GPU on-chip SRAM, performs a single step of the attention mechanism, writes it back to HBM, and repeats this for every single attention step. Instead, Flash Attention loads keys, queries, and values once, fuses the operations of the attention mechanism, and writes them back.
It is implemented for models with custom kernels. You can check out the complete list of models that support Flash Attention [here](https://github.com/huggingface/text-generation-inference/tree/main/server/text_generation_server/models).
Scaling the transformer architecture is heavily bottlenecked by the self-attention mechanism, which has quadratic time and memory complexity. Recent developments in accelerator hardware mainly focus on enhancing compute capacities and not memory and transferring data between hardware. This results in attention operation having a memory bottleneck. **Flash Attention** is an attention algorithm used to reduce this problem and scale transformer-based models more efficiently, enabling faster training and inference.
In the standard attention implementation, the cost of loading and writing keys, queries, and values from High Bandwidth Memory (HBM) is high. It loads keys, queries, and values from HBM to GPU on-chip SRAM, performs a single step of the attention mechanism, writes it back to HBM, and repeats this for every single attention step. Instead, Flash Attention loads keys, queries, and values once, fuses the operations of the attention mechanism, and writes them back.
![Flash Attention](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/flash-attn.png)
It is implemented for supported models. You can check out the complete list of models that support Flash Attention [here](https://github.com/huggingface/text-generation-inference/tree/main/server/text_generation_server/models), for models with flash prefix.
You can learn more about Flash Attention by reading the paper in this [link](https://arxiv.org/abs/2205.14135).