Skip to content

vllm.models.qwen3_5.xpu

Modules:

  • model –

    XPU Qwen3.5 implementation adapted from the NVIDIA eager model.

  • mtp –

    Inference-only Qwen3_5 MTP model.

  • specialized_decode –

    Opt-in small-row MoE fusion over the Qwen3.5 XPU eager backbone.