[Question]: Are there plans to support Qwen3-Next with MTP?

[kjgfjlkj]

System Info

System Information:

• OS:
• Python version:
• CUDA version:
• GPU model(s):
• Driver version:
• TensorRT-LLM version:

Detailed output:

Paste the output of the above commands here

How would you like to use TensorRT-LLM

I saw in the documentation that Qwen3 Next does not support MTP. Is there any plan to add support for these features?

Specific questions:

• Model: qwen3-next
• Use case (e.g., chatbot, batch inference, real-time serving): serving
• Expected throughput/latency requirements:
• Multi-GPU setup needed:

Before submitting a new issue...

• Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

[karljang]

@laikhtewari , Do we have a plan for MTP support for the Qwen3-Next model?
I couldn’t find it on the road map, but I’m just checking.