apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[OPs] Universal optimization and Fix early_stop cuda 700 (#3375)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* delete nonzero

* delete setup_ops_base.py

* check if

* check gcp infer_seed.cpu()

* fix repetition_early_stopper_kernel cuda 700
This commit is contained in:
chen
2025-08-14 22:40:44 +08:00
committed by GitHub
parent 09c979f3dd
commit f0f00a6025
15 changed files with 102 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
custom_ops/gpu_ops/get_output_ep.cc
View File

@@ -109,11 +109,11 @@ void GetOutputEp(const paddle::Tensor& x,
return;
}
void GetOutputStatic(const paddle::Tensor& x, int64_t rank_id, bool wait_flag) {
void GetOutputEPStatic(const paddle::Tensor& x, int64_t rank_id, bool wait_flag) {
GetOutputEp(x, rank_id, wait_flag, 1);
}
void GetOutputDynamic(const paddle::Tensor& x,
void GetOutputEPDynamic(const paddle::Tensor& x,
int64_t rank_id,
bool wait_flag,
int msg_queue_id) {
@@ -125,11 +125,11 @@ PD_BUILD_STATIC_OP(get_output_ep)
.Attrs({"rank_id: int64_t", "wait_flag: bool"})
.Outputs({"x_out"})
.SetInplaceMap({{"x", "x_out"}})
.SetKernelFn(PD_KERNEL(GetOutputStatic));
.SetKernelFn(PD_KERNEL(GetOutputEPStatic));
PD_BUILD_STATIC_OP(get_output_ep_dynamic)
.Inputs({"x"})
.Attrs({"rank_id: int64_t", "wait_flag: bool", "msg_queue_id: int"})
.Outputs({"x_out"})
.SetInplaceMap({{"x", "x_out"}})
.SetKernelFn(PD_KERNEL(GetOutputDynamic));
.SetKernelFn(PD_KERNEL(GetOutputEPDynamic));