Integers for AI: INT8, INT4, Scales, and Zero Points
How integers represent real weights: scales, zero points, per-tensor, per-channel, and per-group, measured on every weight of Qwen3-8B.
int8
1 post
1 post
How integers represent real weights: scales, zero points, per-tensor, per-channel, and per-group, measured on every weight of Qwen3-8B.