Hacker Newsnew | past | comments | ask | show | jobs | submit | dilipray's commentslogin

I faced latency challenges on llama2. So I haven’t used it.

Usually OpenAI response is within 2 seconds, but llama2 takes 20+ seonds for the same.

How are they tackling the performance?


> (when the screenshot was taken - this was in the late 90s BTW)


https://medium.com/unbabel/the-need-for-speed-experimenting-...

> It’s that is not enough to just know some new cool technology, nod along and go about your day with your assumptions unchallenged. You need to find out more, test it out, have a grasp before committing to it, and, if you’re lucky, learn a thing or two in the process.


Apple team will copy this, please get it IP Protected. Don't be another Alfred.


Wrong thread?


Raycaster maybe?


Won't be built in a day


And not with a Greek helmet either!


To my dear American, Let's watch South Park episodes 200 and 201.


Still makes me laugh that Muhammad was in ep.68 and no one cared.


Unless I'm missing something, wasn't that from death threats to the authors?


No it was Comedy Central's decision, certainly not Matt and Trey.


Comedy Central's censorship is a bunch of BS, too.


True that. In terms of technology PayTM and Ola were doing better than Flipkart.


+1 for mentioning PayTM, PayTM is improving silently which almost no one notices.


All the great tech guys are out of Flipkart long ago. Now they just have the crap.


Never noticed this.


I am from India. Am I eligible to apply


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: