SubQ 1.1 Small
(news.ycombinator.com)
1.
2.
Subquadratic – Introducing SubQ 1.1 Small
(news.ycombinator.com)
3.
Show HN: KVBoost – chunk-level KV cache reuse for HuggingFace, 5–48x faster TTFT
(news.ycombinator.com)
4.
FlashAttention-T: Towards Tensorized Attention
(news.ycombinator.com)
Today's top topics:
prime day
amazon
samsung
android authority
openai
zdnet
apple
oracle
galaxy ai
android 16