apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Others] Fix typo (#7280)

Browse Source 
* typo

* typo

* typo

* typo
This commit is contained in:
Echo-Nie
2026-04-14 17:28:22 +08:00
committed by GitHub
parent 9d9d79c457
commit 8819a039c9
24 changed files with 70 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/gpu_ops/fp8_gemm_with_cutlass/fp8_fp8_half_block_gemm.cu
+1 -1
View File
@@ -220,7 +220,7 @@ std::vector<paddle::DataType> CutlassFp8Fp8HalfBlockGemmFusedInferDtype(
}
PD_BUILD_STATIC_OP(cutlass_fp8_fp8_half_block_gemm_fused)
.Inputs({"x", "y", "x_sacle", "y_scale", paddle::Optional("bias")})
.Inputs({"x", "y", "x_scale", "y_scale", paddle::Optional("bias")})
.Attrs({"transpose_x: bool",
"transpose_y: bool",
"output_dtype: std::string",
custom_ops/xpu_ops/src/plugin/src/kernel/kunlun3cpp/quant2d_per_channel.xpu
+2 -2
View File
@@ -694,9 +694,9 @@ __global__ void quant2d_per_channel_cached(
constexpr int PINGPONG_LM_LEN = 512;
constexpr int LM_LEN = PINGPONG_LM_LEN * 2;
constexpr int INPUT_BUF_LEN = 4 * 1024;
constexpr int OUPUT_BUF_LEN = 2 * 1024;
constexpr int OUTPUT_BUF_LEN = 2 * 1024;
constexpr int INPUT_MAX_LEN = INPUT_BUF_LEN / sizeof(TX);
constexpr int OUTPUT_MAX_LEN = OUPUT_BUF_LEN / sizeof(TY);
constexpr int OUTPUT_MAX_LEN = OUTPUT_BUF_LEN / sizeof(TY);
constexpr int INPUT_SIZE =
INPUT_MAX_LEN < OUTPUT_MAX_LEN ? INPUT_MAX_LEN : OUTPUT_MAX_LEN;
__simd__ __shared__ float