8b61b0e397
* fix * fix code * fix format * fix format * fix * fix * addAbs * more Unary * add kernels * fix concat&pooling test code * add softmax/element_wise kernel * fix format * add reshape * support for llama * add maxpooling & flatten * add conv_transpose&&native maxpooling * add conv_transpose * add communication operator * fix * style: fix format * style: fix format * add depthTospace&&resize * add layernorm * format * add gemm * add leakyRelu op * modified format * modified onnx leakyrelu alpha * modified batchnorm * fix gemm & avgpooling * fix: onnx resize op input is none bug * add instancenorm, use layernorm replace instance, error * modiefied format, replace layernorm as instancenorm * fix: onnx resize op input is none bug * add pad2d kernel * modified format * fix op * fix resize * remove sync in op * Update INSTALL_GUIDE_CN.md for ASCEND * Update env.sh * format * fix test_resize * fix resize * fix test_resize_ * fix test_resize_ * add HcclCommDestroy && use default context * install onnxtuntime * install onnx-simplifier * install numpy * fix bug after merge * remove CHECK_RET&LOG_PRINT * fix test_ascend_layernorm * fix test_cuda_resize * fix test_ascend_* * fix format --------- Co-authored-by: Haojie Wang <haojie0429@gmail.com> Co-authored-by: wanghailu <wanghailu@qiyuanlab.com> Co-authored-by: OdinaryWord <sx-hz@163.com> Co-authored-by: xgqdut2016 <kenan_gewei@163.com> Co-authored-by: zhangyunze <z13785159769@163.com> Co-authored-by: Songxin <sx-hz@hotmail.com> Co-authored-by: zhangyue <138768300+zhangyue207@users.noreply.github.com> Co-authored-by: zhangyue <zhangyue@qiyuanlab.com> Co-authored-by: sx941227 <14507528+sx941227@user.noreply.gitee.com> Co-authored-by: zhangyunze <zhangyunze@qiyuanlab.com> Co-authored-by: Chenjie Duan <44265800+kilinchange@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| ascend | ||
| bang | ||
| core | ||
| cuda | ||
| ffi | ||
| intelcpu | ||
| kunlun | ||
| nnet | ||
| operators | ||
| utils | ||
| test.h | ||