Viewing profile — manjunaths

I am running this on 16 GB AMD Radeon 7900 GRE with 64 GB machine with ROCm and llama.cpp on Windows 11. I can use Open-webui or the native gui for the interface. It is made availa…

I have a 7900 GRE, which is the same except less memory. I run Gemma 3, LLama 3.1, the QwQ models and the DeepSeek distilled models using llama.cpp. They run fine, I especially lik…

I tried it on my Radeon 7900 GRE 16GB on Windows 11 WSL Ubuntu 24.04 with torch 2.4.0 and rocm 6.3.4, from here, https://repo.radeon.com/rocm/manylinux/rocm-rel-6.3.4/ . I am impre…

Can we even implement IIR filters to give good performance and scaling at large scale on current architectures like GPUs ?

The contributing page is not loading for me, did we hug it to death?

¦5) Deep breath in and constrict ¦your abdomen and chest and ¦push the breath in the brain (DMT ¦breath) for 10 seconds What?! How do you "push the breath in the brain"? It would h…

https://beyondbackprop.github.io/ This is the NeurIPS workshop that the article is talking about.

> I'm embarrassed that I feel so compelled to post this--on a Friday night at that--I apologize. Don't be. Finding gems like this is why some of us read the comments.

You could use signal for messaging. But why not SMS? It is not like text messaging is owned by anyone like WhatsApp or Telegram. I found that my only requirement for a smart phone …

> Also there are times when I ask a specific question like "What does such and such a library function return?" and they'll say "two strings" but don't know if it's a list or a tup…

It is called the Zeigarnik effect. https://www.psychologistworld.com/memory/zeigarnik-effect-in...

Like automatic differentiation is it possible to use it to integrate too? Kind of like f = ma; a = f/m; velocity = integral (a) dt; position = integral (v) dt ?

I know that it is a common belief that India is 3rd world country and people would jump at any chance to get out. Not all of India is like that and not all of us are wage slaves do…

Oh...wow. This is amazing!

Is it possible to calculate the theoretical performance of a cluster under HPGMG and then do a practical run and come with an efficiency number like in HPL ? One of the biggest rea…