Christos Tzamos @ChristosTzamos · 11 Mar 2026
2/4 The key limitation of LLMs is that standard attention is too slow for any practical computation. We bypass this limitation with a new decoding path that allows for exponentially faster attention enabling almost constant work per token generation. https://t.co/ItoWGDkuPy
59 086Views
741Likes
12Reposts
3Replies
1Quotes
128Bookmarks
Is that a lot?
38.4×vs 10K–100K median1 540 views is typical
2.5× audienceReachviews ÷ followers
1.28%Engagement rateof viewers reacted