Hetzner is working on LLM Inference
(news.ycombinator.com)
1.
2.
DSpark: Speculative decoding accelerates LLM inference [pdf]
(news.ycombinator.com)
3.
OpenAI’s new ‘Jalapeno’ chip is the company’s first step towards the future
(androidauthority.com)
4.
Hypura – A storage-tier-aware LLM inference scheduler for Apple Silicon
(news.ycombinator.com)