Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Increase MoE expert precision and fine-tune on RL rollouts

A mitigation that promotes expert precision and fine-tunes on reinforcement-learning rollouts to reduce quantization-induced generation drift.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See inference quantization for the methods filed beside it.

Filed under inference & serving › inference quantization