apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 16:22:57 +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

4
custom_ops/gpu_ops/sample_kernels/rejection_top_p_sampling.cu
View File

@@ -19,7 +19,7 @@
std::vector<paddle::Tensor> TopPSamplingReject(const paddle::Tensor &probs,
const paddle::Tensor &top_p,
const paddle::optional<paddle::Tensor> &top_k,
int seed) {
int64_t seed) {
std::vector<int64_t> probs_shape = probs.shape();
unsigned int batch_size = probs_shape[0];
unsigned int vocab_size = probs_shape[1];
@@ -82,7 +82,7 @@ TopPSamplingRejectInferDtype(const paddle::DataType &probs_dtype,
PD_BUILD_STATIC_OP(rejection_top_p_sampling)
.Inputs({"probs", "top_p", paddle::Optional("top_k")})
.Outputs({"samples"})
.Attrs({"seed: int"})
.Attrs({"seed: int64_t"})
.SetKernelFn(PD_KERNEL(TopPSamplingReject))
.SetInferShapeFn(PD_INFER_SHAPE(TopPSamplingRejectInferShape))
.SetInferDtypeFn(PD_INFER_DTYPE(TopPSamplingRejectInferDtype));