[Bug]: Implement of TriangleMix

[Espere-1119-Song]

Describe the bug

When I try to apply tri_mix on qwen2.5-7B, I meet the error: Failed to apply TriangleMix: The attn_type tri_mix you specified is not supported.

I test with MInferenceConfig.get_available_attn_types(), but also miss the tri_mix.

How can I apply tri_mix on my LLM?

>>> from minference import MInferenceConfig
To benefit from fast kernel implementations, we recommend installing SGLang or vllm.
>>> supported_attn_types = MInferenceConfig.get_available_attn_types()
>>> supported_attn_types
['minference', 'vllm_minference', 'hf', 'vllm', 'dense', 'static', 'dilated1', 'dilated2', 'a_shape', 'tri_shape', 'vllm_a_shape', 'vllm_tri_shape', 'inf_llm', 'flexprefill', 'vllm_flexprefill', 'xattention']
>>> 

Steps to reproduce

No response

Expected Behavior

No response

Logs

No response

Additional Information

No response

[hzy46]

Hi @Espere-1119-Song , thanks for the support. Tri mix is implemented in latest code.

Please try to git clone the latest code and install minference by pip install -e . instead of directly using pip install minference.

[Espere-1119-Song]

Thanks for your support!!