ulam2

Testing waters, i think

Yes, that is my question too. Someone knowledgeable can comment

> vLLM and SGLang are complex, and bugs are common This for me is the heart of the issue. Feature creep will lead to the downfall of all these frameworks. Today, we can conjure our own bespoke inference engine for our own hardware in no time. It need only support a few modern model architectures. The code can be audited too. I think the article highlights an important gap area for the industry.

Appreciate your feedback. I will try and add sync option.I made this for personal use and thought of sharing since it turned out well.

I personally solved this by using revanced and disabling shorts completely.

And with all the progress in LLMs and MCPs, I thought the number of smartphone OSs would just explode

Folks, this is what bad stats look like. All bot accounts look and behave like this. They didn't even do a systematic study to prove their claims against other bot acconts (which are not associated with deepseek at all).

No base model? disappointed.

I'll consider superintelligence achieved if AI can do such work faithfully.

Blokada (non playstore version)

That's not a smartphone, it's an oversmart phone

Why not have an option for both? Both have their use cases.