Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
1.
▲
Why do math libraries produce different results across platforms?
(github.com/RegularJoe-CEO)
3 points
luxiedge
4 months ago
3 comments
2.
▲
Constant 14ms attention: 512→524K tokens (24.5x faster than FlashAttention)
(github.com/RegularJoe-CEO)
1 point
luxiedge
4 months ago
1 comment
3.
▲
Show HN: O(1) memory attention – 512K tokens in 3.85 GB (eval binary)
(github.com/RegularJoe-CEO)
1 point
luxiedge
4 months ago
discuss