Viewing profile — sabareesh

I am pretty much doing the same but running the coolant at 40 deg C instead of 45 as my pumps are rated for 45 C max temp. Here is bit more about my setup https://sabareesh.com/pos…

Yes this has been on my mind as well. But this was built one at a time but still overall very happy with them

Appreciate the feedback. I have improved the article.

Appreciate the feedback. I have improved the article.

I am primarily experimenting on post training stack. As of now working on training a model that is natively RLM https://github.com/alexzhang13/rlm

It is basically on 2 different circuits/breakers. Asus wrx90e supports 2 psu as well. You may need to synchronize both psu and several adapter for this is available in Amazon. Soon…

Not sure what really happened but some force or bad solder caused it.

Most of the training i am working on is with post training. You can do so much with a system that is running 24/7

Sure 140mm fans you may call little but it does need enough static pressure for the radiators. This setup is already several times quieter than stock setup

Converting four RTX PRO 6000 Blackwell cards to waterblocks, finding a VRM choke loose on the workbench, and getting back to 41k tok/s.

Sounds like speculative decoding but for KV cache

Based on last few attemts on claude code to address a docker build issue this feels like a downgrade

Codex usually dont add itself as contributor so this is misleading .

I wish it provided benchmark comparing Direct RAM offload vs CPU offload vs Full VRAM

Tesla have their own Insurance product which is already very competitive compared to other providers. Not sure if lemonade can beat them . Tesla's insurance product has similar obj…

I am looking for some open source terminal for iphone .I have code server running which i can just use terminal from vs code on safari

Sorry to disappoint. But purely codex and claude code

I have switched to terminal

TL;DR is that they didn't clean the repo (.git/ folder), model just reward hacked its way to look up future commits with fixes. Credit goes to everyone in this thread for solving t…

Non starter for us, we cant ship propriety data to a third party servers.

this has one of the worse score in AA-Omniscience Hallucination Rate

Nope lower is better compared to recent open ai models this is bad. I am looking at AA-Omniscience Hallucination Rate