Search

Showing top 60 results for "NVFP4"

Related topics: NVFP4

Tracked topic

NVFP4

People also ask

What is quantization-aware distillation?

QAD uses the original full-precision model (teacher) to teach the quantized model (student). First, create a quantized model by running PTQ on the full-precision model. Then distill the frozen BF16 model into the quantized model using a KL divergence loss comparing the teacher’s and student’s logits. Figure 1 shows the two-stage QAD process used to build the Nemotron 3.5 Lightning NVFP4 checkpoint. The full-precision BF16 model serves as the frozen teacher and is also the starting point for Stage 1, a PTQ pass that quantizes weights to W4A16 to produce the quantized student. In Stage 2, the st

Developing Nemotron 3.5 Lightning NVFP4 with QAD Using NVIDIA Model Optimizer | NVIDIA Technical Blog