未验证 提交 30fb07ef 编写于 作者: H hong 提交者: GitHub

fix search sort bug (#41664) (#41684)

* fix search sort bug (#41664)

* fix depthwise dnn bug (#41666)
上级 58c99030
......@@ -640,6 +640,7 @@ void DepthwiseConvCudnnGradKernel(const Context& dev_ctx,
bool use_addto,
int workspace_size_MB,
bool exhaustive_search,
bool fuse_relu,
DenseTensor* input_grad,
DenseTensor* filter_grad) {
ConvCudnnGradKernel<T>(dev_ctx,
......
......@@ -431,6 +431,7 @@ void DepthwiseConvCudnnKernel(const Context& dev_ctx,
bool use_addto,
int workspace_size_MB,
bool exhaustive_search,
bool fuse_relu,
DenseTensor* out) {
ConvCudnnKernel<T>(dev_ctx,
input,
......
......@@ -1614,6 +1614,7 @@
func : SearchsortedInferMeta
kernel :
func : searchsorted
data_type : sorted_sequence
# segment_pool
- api : segment_pool
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册