Intel reduces latencies of chat LLM app using quantisation Posted by mariarmestre on Monday May 13, 2024 @06:14AM from the community.intel.com dept. https://community.intel.com/t5/Blogs/Tech-Innovation/Cloud/bg-p/blog-cloud/spr-xeon-gen-ai-ml-part3.html ( 5 comments | 5 points | on HN )
I can't see the post.
I've fixed it above now.