- 23 12月, 2021 1 次提交
-
-
由 Sing_chan 提交于
* block warning when build demo_ci and infer_ut * use build pipe line clone to test
-
- 20 12月, 2021 1 次提交
-
-
由 sneaxiy 提交于
* support FP16 for more ops * add amp list tests * refine reduce_mean_grad * fix OP benchmark ci * fix fp16 reduce_mean * updat ut, but still have some problems * remove mean/reduce_mean fp16 kernel
-
- 15 12月, 2021 1 次提交
-
-
由 jianghaicheng 提交于
* add ipu_inference * resovle commments * resolve comments * add EnableIpu introduction * rm line * restore npu update * add ernie and resnet50 test * fix copyright time Co-authored-by: Nyaozhixin <522190855@qq.com>
-
- 13 12月, 2021 1 次提交
-
-
由 zlsh80826 提交于
* add restriction on plugin supportsFormat to eliminate errors from TensorRT8 * ernie-varlen is only supported on architecture >= sm75
-
- 07 12月, 2021 1 次提交
-
-
由 Zuza 提交于
* quantize slice op * correct test * fix code formatting
-
- 11 11月, 2021 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 09 11月, 2021 1 次提交
-
-
由 Sing_chan 提交于
-
- 04 11月, 2021 1 次提交
-
-
由 wangye707 提交于
-
- 27 10月, 2021 1 次提交
-
-
由 wangxinxin08 提交于
* add dcnv2 plugin
-
- 26 10月, 2021 2 次提交
-
-
由 baoachun 提交于
* fix wrong trt dim when input dim is 2 * update leaky_relu and instance_norm converter unit test * add instance_norm input dim check
-
由 Wangzheee 提交于
[Paddle-Inference]Add MatmulV2ToMatmul convert Pass, fix (matmul_v2, matmul, mul) convert pass, fix (matmul, mul) op_teller (#36652) * new_Matmul2ToMatmulToMul * new_Matmul2ToMatmulToMul * fix paddle_pass_builder * fix paddle_pass_builder * fix paddle_pass_builder * tem * tem * Add MatmulV2ToMatmul convert Pass; MatmulV2ToMul convert Pass * Add MatmulV2ToMatmul convert Pass; MatmulV2ToMul convert Pass * add matmul_broadcast_unitest * fix op_teller
-
- 23 10月, 2021 1 次提交
-
-
由 Huihuang Zheng 提交于
This PR added some changes to match the CINN change for compilation. It also tried to fix JiangCheng's Problem in PR: https://github.com/PaddlePaddle/Paddle/pull/36100 These changes include: 1. Set `CINN_GIT_TAG` to a newer tag 2. CINN now just `make cinnapi -j` 3. We have to add `-DPY_VERSION=${PY_VERSION} -DWITH_TESTING=ON` to CINN cmake args 4. For CINN's third party dependencies, we could just include headers without target_link_libraries 5. Moved `cinn.cmake` from `paddle/cmake` to `paddle/cmake/external` to match old style. External folder contains `lite`, which is the same level of `cinn` 6. CINN added `-DNAMESPACE=cinn_gflags` in `gflags.cmake` to have different gflag namespaces between CINN and Paddle. It solved re-define problem. 7. Change namespace of `::google::` in gflags to `::GFLAGS_NAMESPACE`
-
- 19 10月, 2021 1 次提交
-
-
由 wangxinxin08 提交于
* add nearest_interp_v2 trt plugin
-
- 23 9月, 2021 1 次提交
-
-
由 Peihan 提交于
-
- 22 9月, 2021 1 次提交
-
-
由 Peihan 提交于
* support ernie-int8 test and prune op attribute test * remove using and use namespace * remove macro and use shell instead * Revert "remove macro and use shell instead" This reverts commit 615964b149d7de7825b341936b42be22a4bc0091. * fix grammar error * fix shell error
-
- 16 9月, 2021 1 次提交
-
-
由 Wilber 提交于
-
- 15 9月, 2021 1 次提交
-
-
由 Sing_chan 提交于
-
- 14 9月, 2021 2 次提交
- 07 9月, 2021 1 次提交
-
-
由 Peihan 提交于
* notest,test=inference;support test different suite type * notest,test=inference;fix script bugs * notest,test=inference;fix count time issue * test=document_fix; fix readme grammar
-
- 31 8月, 2021 2 次提交
-
-
由 Shang Zhizhou 提交于
* Revert "Revert "Add copy from tensor (#34406)" (#35173)" This reverts commit 32c1ec42. * add template instantiation
-
由 Peihan 提交于
* change exit code and summary style * disable test_ernie_text_cls on windows
-
- 27 8月, 2021 2 次提交
-
-
由 joanna.wozna.intel 提交于
* Add calculation for gru op * Correct the types * Remove mkldnn only * Correct mkldnn ifdef * Remove mkldnn ifdef * Separate mkldnn quantizer test * Correct Windows test * Check different cmake fix * Revert cmake change * Cmake change 2 * Cmake change 3
-
由 zhangchunle 提交于
This reverts commit ac33c0ca.
-
- 26 8月, 2021 1 次提交
-
-
由 Shang Zhizhou 提交于
* add api * temp save * revert * copytocpu async ok * fix style * copy sync ok * fix compile error * fix compile error * api done * update python async api * fix compile * remove async python api; add c++ async unittest * remove python async api * update unittest * update unittest * add C++ unittest for copytensor * add unittest * update namespace utils to class TensorUtils * add unittest * update unittest * update unittest * update code style * update code style * update unittest
-
- 25 8月, 2021 3 次提交
- 23 8月, 2021 1 次提交
-
-
由 Peihan 提交于
* enable infer_ut on windows * remove lib calculation & time * unset http_proxy when download bos file on windows
-
- 20 8月, 2021 1 次提交
-
-
由 Peihan 提交于
-
- 19 8月, 2021 1 次提交
-
-
由 Peihan 提交于
* add slim resnet50 quant model in pr-ci-inference * enable resnet50_quant multi_thread4_trt_int8_bz1 * remove LOG(FATAL)
-
- 18 8月, 2021 1 次提交
-
-
由 Peihan 提交于
-
- 17 8月, 2021 1 次提交
-
-
由 Peihan 提交于
* add mkl multi-thread test cases * fix codestyle * fix codestyle & enable ernie mkl test
-
- 12 8月, 2021 1 次提交
-
-
由 Peihan 提交于
* add det_mv3_db & LeViT test case in pr-ci-inference * fix LeViT model dir bugs * fix grammar error
-
- 03 8月, 2021 1 次提交
-
-
由 Peihan 提交于
-
- 31 7月, 2021 1 次提交
-
-
由 Peihan 提交于
* add resnet50 trt test in pr-ci-inference test
-
- 14 7月, 2021 1 次提交
-
-
由 Wilber 提交于
-
- 25 6月, 2021 1 次提交
-
-
由 wenbin 提交于
* qkv * ci_test
-
- 21 6月, 2021 1 次提交
-
-
由 Pei Yang 提交于
-
- 17 6月, 2021 1 次提交
-
-
由 Wilber 提交于
[Inference Tensorrt] Add attr for trt engine and handle the input seq problem for ernie var len. (#33575)
-