Petals: Run LLMs at home, BitTorrent-style
(news.ycombinator.com)
1.
2.
Show HN: Tiny-vLLM – high performance LLM inference engine in C++ and CUDA
(news.ycombinator.com)
3.
4.
I’m spending months coding the old way
(news.ycombinator.com)
5.
Spending 3 months coding by hand
(news.ycombinator.com)
6.
I'm spending 3 months coding the old way
(news.ycombinator.com)
8.
How Taalas “prints” LLM onto a chip?
(news.ycombinator.com)
9.
How Taalas "prints" LLM onto a chip?
(news.ycombinator.com)