Skip to content

Commit b6edd15

Browse files
authored
fix scaled_gemm_f8_i4_f16_weight_quantize input (#3685)
1 parent 2fb2c0f commit b6edd15

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

custom_ops/gpu_ops/scaled_gemm_f8_i4_f16_weight_quantize.cu

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -217,7 +217,7 @@ std::vector<paddle::DataType> Fp8Int4WeightQuantizeInferDtype(
217217

218218

219219
PD_BUILD_STATIC_OP(scaled_gemm_f8_i4_f16_weight_quantize)
220-
.Inputs({"intput"})
220+
.Inputs({"input"})
221221
.Attrs({"groupsize: int",
222222
"scale_dtype: std::string"})
223223
.Outputs({"output", "scale"})

0 commit comments

Comments
 (0)