saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-19 19:00:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/onnxruntime/contrib_ops
History
cloudhan 01c5d05712
Avoid repeated GemmSoftmaxGemmPermuteTunableOp<HipT> ctor invocation (#16518) 
The `GemmSoftmaxGemmPermuteTunableOp<HipT>` is expensive to construct,
avoid the ctor invocation will substantially improve the launch time and
get better performance during the decoding. This get <7% e2e time
reduction of whisper large.
2023-07-08 00:25:07 +08:00
..
cpu Enable -Wshorten-64-to-32 warning if available. (#16524) 2023-07-07 08:11:44 -07:00
cuda [CUDA] Optimize BiasGelu/BiasGeluGrad Kernel (#16608) 2023-07-07 08:28:38 +08:00
rocm Avoid repeated GemmSoftmaxGemmPermuteTunableOp<HipT> ctor invocation (#16518) 2023-07-08 00:25:07 +08:00