Skip to content

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

chore: add shared agent config layout (#1700)
Yi Liu committed 6 months ago
8ccf34b
[ARK CI] Enhance auto-round-lib CI test (#1801)
chen, suyue committed 6 months ago
5bbe39b
[refactor] decouple calibaration code (#1765)
Heng Guo committed 6 months ago
71fb350
reduce XPU memory usage in CI (#1812)
Xin He committed 6 months ago
bc54563
set default DYNAMO_CACHE_SIZE_LIMIT to 16 (#1786)
Wenhua Cheng committed 6 months ago
cb9b0b7
Enhance ark test workflow (#1805)
chen, suyue committed 6 months ago
72d7fc8
fix bug of gguf alg ext (#1796)
Heng Guo committed 6 months ago
f64a0d5
fix new arch bug for llmc (#1781)
Heng Guo committed 6 months ago
aa29325
Integrate AutoRound Lib (#1723)
Zhenzhong Xu committed 6 months ago
253117e
support model_free WOQ quantization (#1699)
Xin He committed 6 months ago
f0013f0
b2584b2
add notes (#1795)
Wenhua Cheng committed 6 months ago
68df95b
Fix incompatible weight names (#1759)
Wang, Mengni committed 6 months ago
4c1eb8b
fix amp (#1767)
Wenhua Cheng committed 6 months ago
6add4c2
fix amp (#1768)
Wenhua Cheng committed 6 months ago
8288c48
Optimize CUDA CI and Code Scan workflows (#1770)
Sun, Xuehao committed 6 months ago
a46ad81
871f6f3
clean and fix for new arch (#1761)
Heng Guo committed 6 months ago
1c615f1
Fix hpu error (#1766)
Heng Guo committed 6 months ago
244091f
delete unreproduced results for now (#1760)
ZaneMark committed 6 months ago
ed8eb67
Fix vllm CUDA CI (#1750)
Sun, Xuehao committed 6 months ago
5e2dbdb
New architecture for auto_round (#1542)
Heng Guo committed 6 months ago
91585c7
add support for MiMo-V2-Flash (#1718)
Heng Guo committed 6 months ago
e62d29d