onnxruntime
Support larger hidden size in Attention Cuda kernel
#7002

Merged

Commits

Support larger hidden size in Attention Cuda kernel

gh-yewang committed 5 years ago
Update attention_transpose.cu

gh-yewang committed 5 years ago
review comments

gh-yewang committed 5 years ago
fix typo and add check in quantization

gh-yewang committed 5 years ago
update readme

gh-yewang committed 5 years ago