onnxruntime/include/onnxruntime/core
2021-05-06 16:21:32 -07:00
..
common Revert "Add log to allow serving platforms to quantify ORT usage. (#7476)" (#7598) 2021-05-06 16:21:32 -07:00
eager kerne invoker api for eager mode (#7473) 2021-04-30 13:33:58 -07:00
framework Change onnxruntime::make_unique to std::make_unique (#7502) 2021-04-29 17:04:53 -07:00
graph Add support for setting shape inference function on fused nodes (#7007) 2021-05-05 13:32:07 +10:00
optimizer Enable NHWC transformer when generating ORT format model (#7126) 2021-03-29 18:39:48 +10:00
platform "Sticky" allocation of worker threads (#7551) 2021-05-03 18:28:13 +01:00
providers rename cuda_mem_limit and hip_mem_limit to gpu_mem_limit for both CUDA EP and ROCm EP (#7226) 2021-04-05 09:04:04 -07:00
session Lifhuan/force trt sequential (#7440) 2021-04-28 13:59:37 -07:00