Add Cerebras Integration

[henrytwo]

Why are these changes needed?

Add integration for Cerebras, which provides super low-latency, high speed LLM inference. Currently Llama 3.1-8B/70B are supported.

Tool calling examples have been provided in this PR, which also function with streaming. Additionally, token cost calculations have been implemented.

This PR mirrors the changes from: autogenhub#48

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://microsoft.github.io/autogen/docs/Contribute#documentation to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[henrytwo]

cc: @jackgerrits @afourney

[henrytwo]

Anyone know why these files that I didn't touch are failing the linter? https://github.com/microsoft/autogen/actions/runs/11111974198/job/30874062565?pr=3585#step:6:193

The first few seem legit, but I didn't touch any HTML stuff

[afourney]

The changes look great, and consistent with how other client providers are implemented. I do not have means to test the changes end-to-end, but what I see looks good. I believe there is some small format fixed that are needed to pass the test, but on substance this looks good.

[jackgerrits]

Ah the HTML thing is a line ending issue in main I am pretty sure, I'll open a PR for it

[henrytwo]

Ah the HTML thing is a line ending issue in main I am pretty sure, I'll open a PR for it

Is there something I can do to fix it locally? It's actually breaking my git right now 😢

[jackgerrits]

Ah the HTML thing is a line ending issue in main I am pretty sure, I'll open a PR for it

Is there something I can do to fix it locally? It's actually breaking my git right now 😢

Yeah I had the same thing happen to me... I'm not sure. I'll have what I think is the fix merged in a few mins (just waiting on an approval)

[jackgerrits]

Cool, looks like the HTML file issue is gone, just some other formatting issues to be resolved then we can merge this

[henrytwo]

@jackgerrits can you approve the workflow please? I ran pre-commit locally to format the files