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

Fix FP8 quantizer for Transformers v4 (#1504)
Yi Liu committed 8 months ago
6ab2db2
[bug fix] force ignore mlp.gate (#1501)
Xin He committed 8 months ago
f5f6b05
Update torch to 2.10.0 in CPU CI (#1492)
Sun, Xuehao committed 8 months ago
1e72e6a
Grep core dumped issue in UT test (#1484)
chen, suyue committed 8 months ago
c2152e4
add qwen35 ut (#1482)
Wenhua Cheng committed 8 months ago
2b5d117
support qwen3_5 moe (#1476)
Wenhua Cheng committed 8 months ago
1b37c31
34acefd
Fix cuda ut workflow (#1472)
Sun, Xuehao committed 8 months ago
b55ffb9
support glm5 (#1466)
Wenhua Cheng committed 8 months ago
62c9808
23c16c6
Support load FP8 model on HPU (#1449)
Yi Liu committed 8 months ago
aef6d3c
c0dc55f
[Regression] fix FP8_STATIC loading (#1452)
Xin He committed 9 months ago
9855b4b
Attach `act_max_hook` for FP8 model (#1447)
Yi Liu committed 9 months ago
81c8ee4
bump version (#1445)
chen, suyue committed 9 months ago
0f087c9
fix bug of evaluate_accuracy (#1430)
Xin He committed 9 months ago
40253af
update readme for Intel xpu usage (#1441)
chen, suyue committed 9 months ago
f16d57d