triton VS ollama

There's a ton of cool opportunity in the runtime layer. I've been keeping my eye on the compiler-based approaches. From what I've gathered many of the larger "production" inference tools use compilers:

- https://github.com/openai/triton

Does anyone have more inside knowledge from OpenAI or AMD on AMDGPU support for Triton?

I see this:

https://github.com/openai/triton/issues/1073

But it's not clear to me if we will see AMD GPUs as first class citizens for pytorch in the future?

I thought this was a good overview of the idea Triton can circumvent the CUDA moat: https://www.semianalysis.com/p/nvidiaopenaitritonpytorch

It also looks like they added MLIR backend to Triton though I wonder if Mojo has advantages since it was built on MLIR? https://github.com/openai/triton/pull/1004

I'm pretty happy with the setup, because it allows me to keep all the AI stuff and its dozens of conda envs and repos etc. seperate from my normal setup and "portable". It may have some performance impact (although I don't personally notice any significant difference to running it "natively" on windows), and it may enable some extra functionality, such as access to OpenAi's Triton etc., but that's currently neither here nor there.

Very cool development. There is too much busy work going from development to test to production. This will help to unify everything. OpenAI Triton https://github.com/openai/triton/ is going for a similar goal. But this is a more fundamental approach.

I’m a huge fan of open source models, especially the newly release Llama 3. Because of the performance of both the large 70B Llama 3 model as well as the smaller and self-host-able 8B Llama 3, I’ve actually cancelled my ChatGPT subscription in favor of Open WebUI, a self-hostable ChatGPT-like UI that allows you to use Ollama and other AI providers while keeping your chat history, prompts, and other data locally on any computer you control.

Ollama for running LLMs locally

There are various other interesting options to set, but for those, I will direct you to the link to the documentation. During the OS Day, I had the chance to experiment a bit with the models offered by Ollama; in fact, if you need some inspiration, I invite you to check out the YouTube channel of Shroedinger Hat where you can find the videos of the individual talks, also organized in a single playlist; you will find more than one showing the use of Ollama for various projects and in various ways 😁

That’s where Ollama comes in! Ollama is a free and open-source application that allows you to run various large language models, including Llama 3, on your own computer, even with limited resources. Ollama takes advantage of the performance gains of llama.cpp, an open source library designed to allow you to run LLMs locally with relatively low hardware requirements. It also includes a sort of package manager, allowing you to download and use LLMs quickly and effectively with just a single command.

easiest is probably with ollama [0]. I think the ollama API is OpenAI compatible.

[0]https://ollama.com/

They ended up addressing this issue by including it on the last line of their readme as one of the "Supported backends[sic]".

https://github.com/ollama/ollama/issues/3697

LLM models are challenging to run directly via ONNX runtime on CPU. For these, we are using a GPU-accelerated Ollama server under the hood: