CUDA and Triton implementations of Flash Attention with SoftmaxN.
Project description
The author of this package has not provided a project description
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for flash-attention-softmax-n-0.1.0rc6.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | c976a10f48c12f248fb1d3b36bfb1fc9ec33691ebfe7a4b713f6b5fc810ed253 |
|
MD5 | e70caff7efe70e7fb2f68fba0b1d2a0d |
|
BLAKE2b-256 | 252da1342b986bf86672e8d50958c2f52b2853f0782a3ae6edb6c2ad39ea6a1b |
Close
Hashes for flash_attention_softmax_n-0.1.0rc6-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 73ac8fc2ad25a6bd61db6dd7494dcdc86709c431c39200860de95e06be90d958 |
|
MD5 | c1a679b1ab09eef6c7b32f39b5883c22 |
|
BLAKE2b-256 | 102cf0ccd8d90a0ce40deff97d3ca681a46d37fcef33cddee004b37bd0e39c45 |