Skip to content

Issue: Weight-Only Quantization Not Working for GroupedLinear Modules #725

@jQizhang

Description

@jQizhang

When performing weight-only quantization (e.g., NVFP4) on models with QuantTEColumnParallelGroupedLinear or other GroupedLinear modules, the quantization process fails to properly compute and store the amax values.

It may because GroupedLinear modules use multiple weight parameters (weight0, weight1, weight2, ...) instead of a single weight parameter, and share a single weight_quantizer across all weights.

The existing weight_attr_names() function cannot detect these weight parameters, causing weight_only_quantize() to skip these modules entirely.

Metadata

Metadata

Assignees

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions