- 11 2月, 2022 2 次提交
-
-
由 JingZhuangzhuang 提交于
-
由 Wangzheee 提交于
* support ernie quant model with interleaved * support ernie quant model with interleaved * support ernie quant model with interleaved * support ernie quant model with interleaved * support ernie quant model with interleaved * support ernie quant model with interleaved * support ernie quant model with interleaved
-
- 09 2月, 2022 1 次提交
-
-
由 Wangzheee 提交于
* rebuild matmul pass: trt and gpu_cpu * rebuild matmul pass: trt and gpu_cpu * rebuild matmul pass: trt and gpu_cpu * rebuild matmul pass: trt and gpu_cpu
-
- 06 2月, 2022 1 次提交
-
-
由 Wilber 提交于
-
- 28 1月, 2022 1 次提交
-
-
由 wenbin 提交于
* slice * shuffle pass enhancement
-
- 27 1月, 2022 2 次提交
-
-
由 wenbin 提交于
* shuffle channel pass * add ut * timeout fix * makefile fix
-
由 Wangzheee 提交于
* Paddle-Inference:fix_concat_slice * Paddle-Inference:fix_concat_slice * Paddle-Inference:fix_concat_slice * Paddle-Inference:fix_concat_slice * [Paddle-Inference]: fix concat slice * [Paddle-Inference]: fix concat slice * [Paddle-Inference]: fix concat slice
-
- 25 1月, 2022 1 次提交
-
-
由 Zhang Jun 提交于
* [inference] update convert reduce op&ut,test=develop * update * update * update * add int32 support * add int32 support * add comments * trt < 7.0 do not support int32 * test=develop * update * test=develop
-
- 18 1月, 2022 3 次提交
-
-
由 Zhanlue Yang 提交于
* Merged LoDTensor with Tensor,test=allcases * Patched python level LoDTensor * Patched python level LoDTensor * Merge Tensor into DenseTensor * Fixed namespace issues,test=allcases * Fixed merge issues * Fixed inference issues * Fixed NPU test issues * Fixed merge issues
-
由 JingZhuangzhuang 提交于
* fix trt convert conv2d skip * fix trt convert conv2d skip
-
由 wenbin 提交于
* modify params check * correct compile
-
- 17 1月, 2022 1 次提交
-
-
由 wenbin 提交于
* develop test * throw * ne * wrong cnt
-
- 14 1月, 2022 1 次提交
-
-
由 heliqi 提交于
* add trt_convert_flatten_contiguous_rang op * trt version >7,support trt_convert_flatten_contiguous_rang * trt version >7,support trt_convert_flatten_contiguous_rang * trt version >7,support trt_convert_flatten_contiguous_rang * test cast add trt version >=7 skip
-
- 13 1月, 2022 2 次提交
- 11 1月, 2022 1 次提交
-
-
由 fengkuangxiaxia 提交于
-
- 06 1月, 2022 1 次提交
-
-
由 wenbin 提交于
* bug fix * remove blank
-
- 04 1月, 2022 1 次提交
-
-
由 zlsh80826 提交于
-
- 30 12月, 2021 1 次提交
-
-
由 wenbin 提交于
* dynamic shape clone supported
-
- 17 12月, 2021 1 次提交
-
-
由 Leo Chen 提交于
* Inspect the information inside a TRT engine. * Follow up the google code style. * Fix code error.
-
- 13 12月, 2021 2 次提交
- 09 12月, 2021 1 次提交
-
-
由 Wangzheee 提交于
* fix_ele_convert: IElementWiseLayer can broadcast * fix_ele_convert
-
- 08 12月, 2021 1 次提交
-
-
由 feng_shuai 提交于
fix: when ceil_model==true && Padding_algo!=SAME, (x-size)/stride != int, this convert is wrong (#37929)
-
- 06 12月, 2021 1 次提交
-
-
由 wenbin 提交于
* fix * Update stack_op_plugin.cu comments
-
- 03 12月, 2021 1 次提交
-
-
由 ronnywang 提交于
* refine structure for cuda and rocm * update * update * update * update
-
- 30 11月, 2021 1 次提交
-
-
由 Guoxia Wang 提交于
* support data_format='NHWC' for prelu channel mode
-
- 25 11月, 2021 1 次提交
-
-
由 Wangzheee 提交于
-
- 24 11月, 2021 1 次提交
-
-
由 Wangzheee 提交于
* matmul_convert_int8 * matmul_convert_int8 * matmulconvert_int8 * Matmul_int8_convert: tensor*tensor * Matmul_int8_convert: tensor*tensor * Matmul_int8_convert: tensor*tensor
-
- 23 11月, 2021 2 次提交
-
-
由 wangxinxin08 提交于
* modify code about fp16 of dcnv2 trt
-
由 Wangzheee 提交于
* fix_nearest * fix_nearest * fix_nearest * fix_nearest
-
- 15 11月, 2021 1 次提交
-
-
由 baoachun 提交于
* remove input dim check of activation in op_teller * remove input dim check of concat in op_teller * remove input dim check of clip in op_teller * remove input dim check of scale in op_teller * remove input dim check in op_teller * update attr check of slice in op_teller
-
- 12 11月, 2021 2 次提交
- 11 11月, 2021 1 次提交
-
-
由 Wangzheee 提交于
-
- 01 11月, 2021 1 次提交
-
-
由 wenbin 提交于
* disable int8 * size_t to int
-
- 29 10月, 2021 2 次提交
-
-
由 baoachun 提交于
-
由 wangxinxin08 提交于
-
- 28 10月, 2021 1 次提交
-
-
由 feng_shuai 提交于
* change api for support trt8 * fix:change api
-
- 27 10月, 2021 1 次提交
-
-
由 wangxinxin08 提交于
* add dcnv2 plugin
-