PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
fix typo in backend (#564)
Wenhua Chengeee6db4b548c
diff --git a/auto_round/inference/backend.py b/auto_round/inference/backend.pyindex 7f0ba35d5..c2d589280 100644--- a/auto_round/inference/backend.py+++ b/auto_round/inference/backend.py@@ -128,7 +128,7 @@ BackendInfos['auto_gptq:cuda'] = BackendInfo(device=["cuda"], sym=[True, False],requirements=["auto-gptq>=0.7.1"])-BackendInfos['auto_round:tritonv2'] = BackendInfo(device=["cuda","cpu","xpu"], sym=[True, False],+BackendInfos['auto_round:tritonv2'] = BackendInfo(device=["cuda","xpu"], sym=[True, False],packing_format="int32",dtype=["float16", "bfloat16"],bits=[2, 4, 8],