Skip to content

Lower Quantization Operations #5418

New issue
New issue
Open
Enhancement
Open
Lower Quantization Operations#5418
Enhancement
Assignees
protonu
Labels
MoE Inference nvFP4Get Llama 4, GPT OSS, Deepseek R1, and Qwen3-Next running with performant 4-bit inference
Milestone
Linear quantization Done
@nvMelissa

Description

@nvMelissa
nvMelissa
opened on Oct 21, 2025

Including definition of lowering criteria

Metadata

Metadata

Assignees

Labels

MoE Inference nvFP4Get Llama 4, GPT OSS, Deepseek R1, and Qwen3-Next running with performant 4-bit inference

Type

Enhancement

Projects

No projects

Milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions