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.

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]

@microsoft-github-policy-service agree company="Cerebras"

[henrytwo]

cc: @marklysze, seems like you're working in this area of the codebase :)

[henrytwo]

Moved to autogenhub#48

[jackgerrits]

I see you closed this, did you still want us to review this?

[henrytwo]

I see you closed this, did you still want us to review this?

Yes I still want it to be reviewed, but on Discord I was told to open the PR in the Autogen org instead

[jackgerrits]

We'd be happy to review. Would you be able to reopen it so we're able to merge?

[henrytwo]

@jackgerrits it won't let me reopen this PR, but I opened another one here: #3585

[jackgerrits]

Sounds good thanks!