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
fix: guard zero-division in GGUF quant kernels to avoid NaN block scales (#1909)
4a60b6f Entrpi committed 5 months ago
feat: improve review-pr skill score from 76% to 90% (#1901)
26e2f3a yogesh-tessl committed 5 months ago
Fix slow startup time of pytest coverage for unit tests (#1899)
b58f934 Sun, Xuehao committed 5 months ago
feat: add MXFP4/MXFP8 quantization support (llmc_compressor format) and related tests (#1865)
dc5216c Xin He committed 5 months ago
[step 1]refine code to support all devices in torch and hot fix for gemma4-unified (#1879)
b24e8eb Wenhua Cheng committed 5 months ago
Suppress misleading warning when detecting model type for GGUF export directories (#1887)
fa48924 Liang Lv committed 5 months ago
[ARK] Add bf16 + NHD layout support, refactor sage_dynamic_quant (#1882)
08c5d6d Luo Yu committed 5 months ago
Fix packing format in quantization config and update variable assignment in tests (#1857)
64c0a5b Xin He committed 5 months ago
Fix Qwen Omni quantization model issue for long form audio generation (#1698)
b403407 Liang Lv committed 5 months ago