Suffian Khan 225439193e Optimize Concat and Split on CUDA to eliminate host-to-device copies when sizes are all the same (#8833) ... * special case concat and split when sizes are equal * add tests for 16 and 32 inputs with same dim * add tests for 16/64 inputs on concat or 16/64 outputs on split * try eliminate windows warning * outter => outer		2021-09-01 15:25:45 -07:00
..
orttraining	Optimize Concat and Split on CUDA to eliminate host-to-device copies when sizes are all the same (#8833)	2021-09-01 15:25:45 -07:00
pytorch_frontend_examples	Sync ORTModule branch with master and fix tests (#6526)	2021-02-02 08:59:56 -08:00
tools	Add hugging-face models loss curve and performance guards to ROCm CI pipeline. (#8915)	2021-09-01 09:03:10 -07:00