Skip to content

vllm.model_executor.layers.quantization.online

Modules:

  • base –
  • fp8 –
  • int8 –
  • moe_base –
  • mxfp4 –

    Online MXFP4 (microscaling FP4, block-32) quantization methods.

  • mxfp8 –

    Online MXFP8 (microscaling FP8, block-32) quantization methods.

  • nvfp4 –