- 12 1月, 2022 2 次提交
-
-
由 JingZhuangzhuang 提交于
* multithread_memory_optimize
-
由 JingZhuangzhuang 提交于
-
- 11 1月, 2022 1 次提交
-
-
由 wangxinxin08 提交于
* add mish trt plugin, compile & install success, run error. test=develop * modify code of mish plugin * upgrade mish trt plugin * modify code according to review * add TRT_NOEXCEPT for mish trt plugin * add unittest for mish trt plugin * remove unnecessary check of mish in op_teller.cc * fix some problem of trt8 * add check and modify unittest while converting mish to trt plugin Co-authored-by: Ndengkaipeng <dengkaipeng@baidu.com>
-
- 05 1月, 2022 1 次提交
-
-
由 Wilber 提交于
-
- 29 12月, 2021 1 次提交
-
-
由 Guoxia Wang 提交于
* support data_format='NHWC' for prelu channel mode (#37019) * support data_format='NHWC' for prelu channel mode * fix prelu weight shape for NHWC of static mode (#38310)
-
- 13 12月, 2021 1 次提交
-
-
由 Wangzheee 提交于
* fix_ele_convert: IElementWiseLayer can broadcast * fix_ele_convert
-
- 10 12月, 2021 1 次提交
-
-
由 Shang Zhizhou 提交于
fix: when ceil_model==true && Padding_algo!=SAME, (x-size)/stride != int, this convert is wrong (#37929) (#38033) Co-authored-by: Nfeng_shuai <fengshuai03@baidu.com>
-
- 08 12月, 2021 1 次提交
-
-
由 wenbin 提交于
-
- 03 12月, 2021 1 次提交
-
-
由 baoachun 提交于
-
- 23 11月, 2021 2 次提交
-
-
由 JingZhuangzhuang 提交于
-
由 JingZhuangzhuang 提交于
-
- 17 11月, 2021 4 次提交
-
-
由 Wangzheee 提交于
* fix_qkv_plugin: half_scale * [Paddle-Inference] fix_qkv_plugin: fix half scale
-
由 Wangzheee 提交于
-
由 Wangzheee 提交于
-
由 JingZhuangzhuang 提交于
-
- 16 11月, 2021 1 次提交
-
-
由 石晓伟 提交于
Co-authored-by: NPei Yang <peiyang@baidu.com>
-
- 29 10月, 2021 1 次提交
-
-
由 Wilber 提交于
-
- 28 10月, 2021 1 次提交
-
-
由 feng_shuai 提交于
* change api for support trt8
-
- 27 10月, 2021 2 次提交
-
-
由 wenbin 提交于
Co-authored-by: Nzlsh80826 <zlsh80826@gmail.com>
-
由 baoachun 提交于
-
- 26 10月, 2021 6 次提交
-
-
由 Wilber 提交于
-
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) (#36737)
-
由 Steffy-zxf 提交于
* Add FasterTokenizer Operator (#34491) Add Tokenizer related functionalities for Transformer model in order that the process of training and predicting is consistent. * support the text string as an input Tensor * support the "VOCAB"unordered_map<wstring, int> as an input Tensor to lookup tokens * Tokenizer used for BERT. This tokenizer applies an end-to-end, text string to wordpiece tokenization. * It first applies basic tokenization, followed by wordpiece tokenization. * optimize fast tokenizer * remove const_cast Co-authored-by: Nzhoushunjie <zhoushunjie@baidu.com> Co-authored-by: Nwawltor <fangzeyang0904@hotmail.com>
-
由 feng_shuai 提交于
-
由 feng_shuai 提交于
-
- 25 10月, 2021 7 次提交
-
-
由 Wilber 提交于
-
由 Wilber 提交于
-
由 Wilber 提交于
cherry-pick prs #36568 fix fc fuse compat problem #36610 support lite xpu choose device id #36010 update lite branch #36628 add file exists check
-
由 JingZhuangzhuang 提交于
-
由 wenbin 提交于
-
由 JingZhuangzhuang 提交于
-
由 JingZhuangzhuang 提交于
-
- 20 10月, 2021 1 次提交
-
-
由 Wilber 提交于
-
- 19 10月, 2021 1 次提交
-
-
由 Wilber 提交于
-
- 12 10月, 2021 1 次提交
-
-
由 wenbin 提交于
-
- 27 9月, 2021 1 次提交
-
-
由 Wilber 提交于
-
- 24 9月, 2021 2 次提交
-
-
由 Wilber 提交于
* update xpu version
-
由 JingZhuangzhuang 提交于
-
- 22 9月, 2021 1 次提交
-
-
由 baoachun 提交于
-