Live data from Hacker News

Intel reduces latencies of chat LLM app using quantisation

community.intel.com

Post reply on HN

Print view View original

1–6 of 6 posts

Intel reduces latencies of chat LLM app using quantisation

#1

Post by mariarmestre » Mon, May 13, 2024, 10:14 AM UTC

Intel reduces latencies of chat LLM app using quantisation
community.intel.com

Re: Intel reduces latencies of chat LLM app using quantisation

#2

Post by thenaturalist » Mon, May 13, 2024, 10:44 AM UTC

Only me or does the link also refer to general blog index for others?

I can't see the post.

Re: Intel reduces latencies of chat LLM app using quantisation

#3

Post by Havoc » Mon, May 13, 2024, 10:44 AM UTC

Bad link? This just takes me to an article index listing

Re: Intel reduces latencies of chat LLM app using quantisation

#4

Post by rrr_oh_man » Mon, May 13, 2024, 10:49 AM UTC

Here's (probably) the correct link: https://community.intel.com/t5/Blogs/Tech-Innovation/Cloud/T...

Re: Intel reduces latencies of chat LLM app using quantisation

#5

Post by mariarmestre » Mon, May 13, 2024, 1:10 PM UTC

Sorry, this is the link: https://community.intel.com/t5/Blogs/Tech-Innovation/Cloud/T...

Re: Intel reduces latencies of chat LLM app using quantisation

#6

Post by dang » Tue, May 14, 2024, 8:54 PM UTC

mariarmestre wrote: post #5

Sorry, this is the link: https://community.intel.com/t5/Blogs/Tech-Innovation/Cloud/T...

Our software changes submitted links to canonical URLs when it finds them, and that page has the canonical URL https://community.intel.com/t5/Blogs/Tech-Innovation/Cloud/b....

I've fixed it above now.

Post reply on HN