Add OLMo model

[janimo]

Support for OLMo models

Note: Only the new ones with -hf suffix are supported, not the old ones built before OLMo was integrated into transformers, those are deprecated and have an extra package requirement.

https://huggingface.co/collections/allenai/olmo-suite-65aeaae8fe5b6b2122b46778

[merrymercy]

Thanks for the contribution. Can you add it here

sglang/test/srt/models/test_generation_models.py

Lines 52 to 56 in f1088e0

	ALL_OTHER_MODELS = [
	ModelCase("Qwen/Qwen2-1.5B"),
	ModelCase("Qwen/Qwen2.5-14B-Instruct"),
	ModelCase("HuggingFaceTB/SmolLM-135M-Instruct"),
	]

and run the test

sglang/docs/en/model_support.md

Lines 16 to 23 in f1088e0

	### Add the model to the test suite
	To make sure the new model is well maintained in the future, it is better to add it to the test suite.
	You can add it to the `ALL_OTHER_MODELS` list in the [test_generation_models.py](https://github.com/sgl-project/sglang/blob/main/test/srt/models/test_generation_models.py) and run the following command to test it.
	For example, if the model is Qwen/Qwen2-1.5B
	```
	ONLY_RUN=Qwen/Qwen2-1.5B python3 -m unittest test_generation_models.TestGenerationModels.test_others
	```

?

[janimo]

I had to bump the error tolerance for decode for the test to pass. The resulting tokens are all the same.

[zhyncs]

@janimo Could you submit another PR to replace this with SGLang's linear?

[janimo]

@zhyncs done #1696