vllm.model_executor.layers.quantization.online

Modules:

• base –
• fp8 –
• int8 –
• lm_head –

  Online-quantized copies of an already-loaded lm_head.

• moe_base –
• mxfp4 –

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

• mxfp8 –

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

• nvfp4 –
• requantization –
• shared_expert –