vllm.models.kimi_k3.amd

Modules:

• kda_metadata –

  ROCm Kimi-K3 specialization of GDN attention metadata.

• latent_moe_runner –
• linear –
• mla –

  AMD-specific MLA wrapper for Kimi-K3.

• model –

  Kimi-K3 multimodal model implementation for vLLM.

• mtp –

  Inference-only Kimi-K3 Multi-Token-Prediction (MTP) draft model.

• ops –