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

Update auto-round-lib README.md (#1437)
chen, suyue committed 9 months ago
232b1da
Enable new cpu test pool (#1435)
chen, suyue committed 9 months ago
0c7f4af
Update diffusion README (#1439)
Wang, Mengni committed 9 months ago
6e786c9
a554a10
fix CUDA CI (#1431)
Xin He committed 9 months ago
d0f3cd0
Fix cuda model ut [glm4][Molmo] (#1428)
Tang Kaihui committed 9 months ago
16a18d7
fix bug in PR-1244 (#1422)
Xin He committed 9 months ago
81383e9
520214a
Update torch to 2.9.1 in CI (#1313)
Sun, Xuehao committed 9 months ago
0cac849
adapt vllm_ext to new extra config (#1409)
Wang, Mengni committed 9 months ago
d2b1fed
refine qwen3_vl_moe experts forward (#1413)
Weiwei committed 9 months ago
2824c37
[LLMC] Wrap block for DDP (#1407)
Yi Liu committed 9 months ago
9920441
Enable xpu test for CI (#1352)
chen, suyue committed 9 months ago
4bcebe7
support llm dynamic wint8aint8 export (#1376)
Wang, Mengni committed 9 months ago
c9f6155
align scale for MLA kv (#1395)
Yi Liu committed 9 months ago
a267625
a12e3f5
Fix version (#1393)
Sun, Xuehao committed 9 months ago
68d07bf
fix layer config (#1373)
Wenhua Cheng committed 9 months ago
4064c4f