not working says deployment not found

why does ollama engine has to change to support new models? every time a new model comes ollama has to be upgraded.

Because of things like this: https://github.com/ggml-org/llama.cpp/issues/12637

Where "supporting" a model doesn't mean what you think it means for cpp

Between that and the long saga with vision models having only partial support, with a CLI tool, and no llama-server support (they only fixed all that very recently) the fact of the matter is that ollama is moving faster and implementing what people want before lama.cpp now

And it will finally shut down all the people who kept copy pasting the same criticism of ollama "it's just a llama.cpp wrapper why are you not using cpp instead"

There's also some interpersonal conflict in llama.cpp that's hampering other bug fixes https://github.com/ikawrakow/ik_llama.cpp/pull/400

What the hell is going on there? It’s utterly bizarre to see devs discussing granting each other licences to work on the same code for an open source project. How on earth did they end up there?

There seems to be some bad blood between ikawrakow and ggerganov: https://github.com/ikawrakow/ik_llama.cpp/discussions/316

But he's talking about a MIT License!

WTF

My guess is that there's money involved. Maybe a spat between an ex-employee and their ex-employer?

Wait, what hosted APIs is Ollama wrapping?

very nice demo. I saw that you are using threejs but when i checked network logs its not downloading it which is great. Are you doing SSR?

Thank you. I am using https://globe.gl/ which wraps three.js. The page realtime page is still pretty slow to load so though.

I'm using Next.js but I'm using all client-side components. The tooling around SPA client side state is just really good so I don't see a huge reason to go full SSR, especially when SEO doesn't matter for the actual app.

water, look at indus water treaty for more details. As per last report it is in abeyance neither suspended nor terminated. Not sure what it means.

very nice. I wanted something like this for Parquet but couldn't find one, this one looks great.

i have come to the same conclusion! It has talent and resources but execution is mired because of bureaucracy, litigation's, politics.

india does not lacks it, its not price competitive as compared to china which has better supply chain and economy of scale.

India and other countries are not going in fab for jobs but for self-reliance.

Going for high-value semicon later is similar to the logic of removing poverty first before investing in space tech. It doesn't work that way.

India had sound policies it was quite ahead of time when it created SCL, check this video for more https://www.youtube.com/watch?v=isBYV6QWDIo it does lacks execution though and had some bad luck.

India does have 130nm plants right now its obsolete node but works fine for low volume needs of its govt.

When SCL was created we were probably 2-3 generations behind.

Now we’re 14 generations behind.

Jumping to 28nm would be progress, especially for mundane devices which go into automotive and white goods.

28nm from the article

there are too many blogs missing from it

interesting, i generally use artist mode in emacs but this seems to have more options.