Ground Truth.
AI, checked against the source.

← All topics

model-compression

Everything on Ground Truth tagged “model-compression” — 1 item.

Nvidia's 'Puzzle' pipeline shrinks a 120B model to 75B and roughly doubles serving throughput News

Nvidia's Nemotron-3-Puzzle compresses a 120-billion-parameter model down to 75 billion using a multi-stage pipeline of pruning, distillation, and quantization -- roughly doubling throughput on a B200 node and lifting single-H100 concurrency at long context from one request to eight.