vllm.models.qwen3_5.nvidia.ops

Modules:

• fused_allreduce_norm_quant –

  TP all-reduce + residual add + Gemma RMSNorm + consumer input quant.

• fused_gdn_gated_norm –
• fused_norm_quant –

  Gemma (1 + w) add-RMSNorm fused with the consumer linear's input quant.