- 17 11月, 2021 1 次提交
-
-
由 Wangzheee 提交于
* fix_qkv_plugin: half_scale * [Paddle-Inference] fix_qkv_plugin: fix half scale
-
- 17 9月, 2021 1 次提交
-
-
由 feng_shuai 提交于
* broadcast qkv_op * use PADDLE_ENFORCE_GT to replace assert
-
- 20 7月, 2021 1 次提交
-
-
由 zlsh80826 提交于
* add trt noexcept definition * add trt noexcept on trt plugin * add trt noexcept on trt int8 calibrator * remove noexcept on base serialize * add trt noexcept on split plugin * add trt noexcept on elementwise plugin * add trt noexcept on prelu plugin * add trt noexcept on pool plugin * add trt noexcept on swish plugin * add trt noexcept on gelu plugin * add trt noexcept on layer norm plugin * add trt noexcept on instance norm plugin * add trt noexcept on emb eltwise layernorm plugin * add trt noexcept on qkv2context plugin * add trt noexcept on skip layernorm plugin * add trt noexcept on slice plugin * add trt noexcept on hard swish plugin * add trt noexcept on stack plugin * add trt noexcept on special slice plugin * add trt noexcept on anchor generator plugin * add trt noexcept on yolobox plugin * add trt noexcept on roi align plugin * add trt noexcept on gather nd plugin
-
- 12 7月, 2021 1 次提交
-
-
由 zlsh80826 提交于
* add trt LT version helper * upgrade PluginTensorRT to IPluginV2Ext * trt plugin factory is not usable in IPluginV2 * upgrade add plugin api to use IPluginV2 * remove IPlugin register and adapt getSerializeSize(), serialize() * adapt IPluginV2Layer * downgrade to IPluginV2 * implement elementwise clone * add gelu plugin creator and fix gelu serialization bug * add swish plugin creator and fix swish serialization bug * format * fix typo * add elementwise plugin creator and fix serialization * add base creator class * add gelu plugin creator * add hard swish creator and fix serialization * add instance norm creator and fix serialization * add layer norm creator and fix serialization * add pool creator and fix serialization * add prelu creator and fix serialization * add slice creator and fix serialization * add swish creator and fix serialization * add instance norm op unittest * remove redundent api * fix wrong graph size to enable trt * instance norm function move to cc * add trt elementwise ut to trigger coverage * remove opt cahce to hit serialization coverage * remove opt cahce to hit serialization coverage * remove unused code * remove unused inputs_ * add dbg info * remove dbg info * add instance norm serialization * roll back * remove comment code * remove trt plugin registery * fix prelu dynamic serialization * add prelu ut and reduce the input size to reduce memory usage * fix pool dynamic plugin serialization and add ut * refine pool ut with subtest * add env for avoiding oom * reduce test input size & increase pool op ut to 45s * add the contributor * remove copyright (will add in contributor) * remove copyright (will add in contributor)
-
- 25 6月, 2021 1 次提交
-
-
由 wenbin 提交于
* qkv * ci_test
-
- 29 4月, 2021 1 次提交
-
-
由 zlsh80826 提交于
* implement MHA order same as training * fix fp16 compile issue on old architecture * fix format * fix format
-
- 23 3月, 2021 1 次提交
-
-
由 Shang Zhizhou 提交于
* fix tensorrt output varible reshape * move padding shape x 1 x 1 in ernie to qkv and fc * update layer name * fix softmax when input is dynamic, fc not padding any more * fix varlen * move fc x_dim assert to op_teller
-
- 27 11月, 2020 1 次提交
-
-
由 Shang Zhizhou 提交于
* remove -DSUPPORTS_CUDA_FP16 in cuda.cmake * comile with cuda9 * add some unittest * notest;test=coverage * add unittest for trt plugin swish && split * update ernie unittest * fix some error message * remove repeated judgement of CUDA version in mbEltwiseLayerNormOpConverter * fix comile errror when CUDA_ARCH_NAME < Pascal" * fix comile error * update unittest timeout * compile with cuda9 * update error msg * fix code style * add some comments * add define IF_CUDA_ARCH_SUPPORT_FP16 * rename IF_CUDA_ARCH_SUPPORT_FP16 to CUDA_ARCH_FP16_SUPPORTED
-
- 05 8月, 2020 1 次提交
-
-
由 Pei Yang 提交于
* develop dynamic shape serilization * add test param for gelu * fix bugs * delete redundant comments * debug * fix conflict. test=develop * fix bug. test=develop * add trt dynamic shape serialized support * fix ernie serialized bug test=develop * fix codestyle test=develop * fix bug test=develop * fix bug.test=develop * modify cmakelist test=develop * fix bug test=develop * fix error message. test=develop * fix trt register plugin based on pr#25003 * add trt dynload * fix deserialization bug of not finding plugin registration * refine code style * recover engine key in tensorrt_subgraph_pass * for ci coverage * add unittest for deserialization Co-authored-by: Nhaozech <chenhaoze94@gmail.com>
-
- 10 7月, 2020 1 次提交
-
-
由 Jeng Bai-Cheng 提交于
Use vector instruction (LDG.128) to improve qkv transpose. It provides 1.4X speedup at same GPU base frequency. test=develop
-
- 07 7月, 2020 1 次提交
-
-
由 Zhaolong Xing 提交于
* fix multhead matmul's instable test=develop * fix multihead matmul bug test=develop * fix converage problem test=develop
-
- 26 3月, 2020 1 次提交
-
-
由 Zhaolong Xing 提交于
* add dynamic plugin support. test=develop * change emb eltwise layernorm to math function test=develop * add emb eltwise layernorm test=develop * can run dynamic shape ernie test=develop * fix ci test=develop * add ut for trt ernie dynamic test=develop * refine dynamic shape c++ interface. test=develop * fix comments test=develop * fix comments test=develop
-