vllm.models.kimi_k3.amd ¶
Modules:
-
kda_metadata–ROCm Kimi-K3 specialization of GDN attention metadata.
-
latent_moe_runner– -
linear– -
model–Kimi-K3 multimodal model implementation for vLLM.
-
mtp–Inference-only Kimi-K3 Multi-Token-Prediction (MTP) draft model.
-
ops–