onnxruntime
Add GPU kernels for ROCm EP
#5655
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
6
Changes
View On
GitHub
Commits
Adding back ROCm kernels by reverting 3a997e7a9 "move rocm kernels to a seperate PR."
Weixing Zhang
committed
6 years ago
like lamb, multi-tensor-apply needs to be disabled for IsAllFiniteOp and ReduceAllL2
Weixing Zhang
committed
6 years ago
address comments from code review.
Weixing Zhang
committed
6 years ago
Use hipMemsetAsync and add checks on HIP calls.
jessebenson
committed
6 years ago
move the generated files to build folder.
Weixing Zhang
committed
6 years ago
Merge branch 'master' into wezhan/rocm1
weixingzhang
committed
6 years ago
Loading