PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
Commits on main
FIXBUG: CPU Offloading for Cache Blocks in Low-Memory GPU Systems or Single GPU on ROCM Configs (#703)
6180041 JartX committed 1 year ago
support for static activation quantization calibration with group_size (#693)
6afe07c Heng Guo committed 1 year ago
support static global scale for nvfp4 and update readme (#691)
4a3530f Wenhua Cheng committed 1 year ago
fix bugs of export deepseek gguf format when iters=0 and q3k accuracy (#665)
923683a Heng Guo committed 1 year ago