Skip to content

[quantization] GPTQ for Qwen3 VLM #548

@stamalakhov

Description

@stamalakhov

What

Let's test/improve GPTQ for VLM models like Qwen3-VL (both vision/text).

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions