Issues
- 0
windows源码编译失败
#970 opened by nicheng0019 - 1
Linux ARM cpu平台,ppl 跑conv winogradb4f3 出现结果mismatch
#969 opened by bin913 - 0
请问一下 No Pad优化的实现在代码中哪个位置呢
#965 opened by KindredSpirithub - 0
请问算子融合的实现主要在哪里呢?
#964 opened by KindredSpirithub - 0
pplnn cpu 推理 异常crash
#963 opened by zjzjwang - 1
不支持 SpaceToDepth 算子
#961 opened by alexliyang - 1
cuda build error
#944 opened by hyaihjq - 0
build pplnn error
#959 opened by alexliyang - 1
When I run build.sh to compile the project, a compilation error occured.
#948 opened by ZhenyiWang0216 - 0
ARM平台是否可以跑int8的推理
#931 opened by bin913 - 0
多模型pipeline的示例
#912 opened by OMG59E - 0
- 4
关于全局engine,其他线程引用导致的性能下降问题
#892 opened by OMG59E - 0
Crash with ONNX Split operator
#891 opened by abcdrm - 4
- 3
- 4
Floating point exception (core dumped) ?
#829 opened by brilliant-yan - 0
使用x86 engine运行resnet50 fp16 onnx模型 core dump
#837 opened by zhnin - 2
- 1
Install Error
#819 opened by aChang146 - 2
获取模型推理结果(GetOutputs)耗时长
#806 opened by 111qqz - 5
- 3
如何使用cmake的将ppl.nn和依赖ppl.nn的代码一同编译?
#800 opened by 111qqz - 2
malloc_consolidate(): invalid chunk size
#797 opened by 111qqz - 1
pplnn save-input 得到的NDARRAY的 shape不正确
#798 opened by 111qqz - 3
linux compile error protobuf static assertion failed
#796 opened by 111qqz - 7
pplnn run mobilenet v2 model failed. (use cuda)
#770 opened by shiwenloong - 2
Onnx run error
#697 opened by XuMicoder - 1
Slice op question
#734 opened by lucasjinreal - 0
请问支持int8在高通芯片上cDSP进行推理吗?
#714 opened by Stephenfang51 - 1
交叉编译RISCV平台可执行文件报错
#662 opened by irexyc - 1
Floating point exception (core dumped)
#689 opened by pangr - 1
- 0
x86支持fp16推理吗?支持的话输入数据是要转为fp16类型或者还是用fp32数据推理过程会自动转为fp16?pplnn目前只支持T4 gpu吗 别的gpu支持吗
#559 opened by royywang - 0
ppl推理问题 runtime.Run()执行次数不同,单次推理时间不同,对于resent50,Run10次,单次ppl_speed是4.7,Run1000次,单次ppl_speed是23.4
#581 opened by geniusjunjun - 0
PPL.NN slower than onnxruntime
#637 opened by lucasjinreal - 1
ubuntu python build failed....
#636 opened by lucasjinreal - 0
x86 build failed;
#634 opened by lucasjinreal - 1
Bilieaner resize support
#648 opened by lucasjinreal - 0
macOS arm M1 build error
#633 opened by lucasjinreal - 3
macOS arm m1 build error
#632 opened by lucasjinreal - 1
error
#631 opened by wm901115nwpu - 9
【gemm_fp32_fma performance】常用shape下,gemm_fp32_fma和tensorflow1.15 eigen matmul性能几乎持平?
#619 opened by huangmiumang - 12
cuda convolution kernel input question.
#561 opened by leiwen83 - 2
compile error
#599 opened by wm901115nwpu - 1
- 9
[CUDA] `RuntimeBuilder.Preprocess()` causes subsequent CUDA function calls to fail
#598 opened by lzhangzz - 3
Error when both CUDA and x86 engines are enabled.
#592 opened by lzhangzz - 0
error using DBNet models
#579 opened by lzhangzz - 5