kelvindelrosario

kelvindelrosario

👤 Developer

1 repository on SrcLog

View on GitHub
1 Repos
2 Stars
0 Forks
2 Watchers

Repositories (1)

flash-attention-with-sink kelvindelrosario/flash-attention-with-sink Python

🐙 Implements Flash Attention with sink for gpt-oss-20b; includes test.py. WIP backward pass, varlen support, and community sync to return softmax_lse only.

2