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

fix typo in backend (#564)

Wenhua Chengeee6db4b548c
diff --git a/auto_round/inference/backend.py b/auto_round/inference/backend.py
index 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],