Skip to content

Releases: AminRezaei0x443/memory-efficient-attention

0.1.3

27 Mar 13:08
@AminRezaei0x443 AminRezaei0x443
0.1.3
1bc0d9e
Compare
Choose a tag to compare
0.1.3 Latest
Latest 
update: bump version
Assets 2
Loading

0.1.2

07 Mar 18:48
@AminRezaei0x443 AminRezaei0x443
0.1.2
dccd556
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
0.1.2

What's Changed

This update fixes torch device handling issues in code. GPU and other kinds of tensors can be used safely.

New Contributors

  • @yhgon made their first contribution in #5

Full Changelog: 0.1.1.0...0.1.2

Contributors

yhgon
Assets 2
Loading

0.1.1

03 Feb 16:08
@AminRezaei0x443 AminRezaei0x443
0.1.1.0
f0add8e
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
0.1.1

Added mask, bias calculation functions for custom and memory efficient chunks computation. So now sublinear memory computation mask, bias are possible.

Full Changelog: 0.1.1...0.1.1.0

Assets 2
Loading

0.1.0

18 Dec 20:37
@AminRezaei0x443 AminRezaei0x443
0.1.0
65556b0
Compare
Choose a tag to compare
0.1.0 
feature: github publish workflow
Assets 2
Loading