- 12 4月, 2022 2 次提交
-
-
由 feng_shuai 提交于
* strided_slice * fix: compiler error because of size() * fix: warning * fix : warning * init input_shape * fix:forget punctuation
-
由 feng_shuai 提交于
* add trt supoort for slice op * fix:output dims bug * fix: test * fix:for c++ coverage * fix:c++ coverage * fix: fix test bug * fix: CI test
-
- 05 4月, 2022 2 次提交
-
-
由 wangxinxin08 提交于
* add fake index and unittest for multiclass_nms3 trt * modify unittest
-
由 Leo Chen 提交于
* enable new executor by default * enable stream safe allocator * test=document_fix;test=coverage * do not use scope in op kernel * fit empty program for new executor * fix communication depend * fix test_sync_batch_norm * skip unsupported place * refine datatransfer * fit for dirtributed program * fix dependencpy * fix some ut
-
- 04 4月, 2022 1 次提交
-
-
由 Sławomir Siwek 提交于
* DRY * change nodes names * add const prefix * change asX to as_x in all files
-
- 02 4月, 2022 2 次提交
-
-
由 Wangzheee 提交于
* paddle inference support new quant_model
-
由 wangxinxin08 提交于
* filter unsupported inputs for elementwise op in op teller * add unittest for corner case
-
- 01 4月, 2022 1 次提交
-
-
由 chentianyu03 提交于
* add interploate cpu kernel * fix nullptr bug * add interpolate gpu kernel * fix unit test error * remove raw kernels * add cuda kernel impl * add infermeta * recover accidentally deleted kernels in interpolate op * fix grad x_grad name error * remove interpolate_v2_op.h * rm unused codes * fix xpu build error * fix build error * fix namespace error * add register header for nup * fix infermeta error * modify by review * add the missing args in test_trt_convert_nearest_interp_v2
-
- 31 3月, 2022 2 次提交
-
-
由 wangxinxin08 提交于
* add multiclass_nms3 converter
-
由 heliqi 提交于
* add flatten2,reshape2,squueze2_trt_fuse_pass test cast * add flatten2,reshape2,squueze2_trt_fuse_pass test cast * add flatten2,reshape2,squueze2_trt_fuse_pass test cast
-
- 29 3月, 2022 1 次提交
-
-
由 wangxinxin08 提交于
* add elementwise sub and elementwise div in tensorrt op teller * add unittest of elementwise mul, sub and div
-
- 19 3月, 2022 1 次提交
-
-
由 hong 提交于
* add infer meta; test=develop * add histogram infer meta; test=develop * fix unitest bug; test=develop * format; test=develop * format; test=develop * bn not use new infer meta; test=develop * add infer meta; test=develop * fixbug; test=develop * fix bug; * recover unitest; test=develop
-
- 15 3月, 2022 1 次提交
-
-
由 Jacek Czaja 提交于
* - Prototype of third solution - fix - compilation fixes - fix - fixe - fix - fix - compilation fix - comment fix - lint update mkldnn conv_elementwise_add_fuse_pass ut - NHWC changes to prelu - alhpa dims - UT fix - fix to UT - lint - Some fixes - added to BWD of prelu NHWC support - reverted removal of resetting cu_layout in clearing of caching * - Small changes * - compilation fix * - fix * - fix * lint * - fixes after internal review * - compilation fix * - lint
-
- 14 3月, 2022 1 次提交
-
-
由 Tomasz Socha 提交于
* Add elementwise add and activation fuse pass * Fix copy ellision * More flexible pattern detector * More flexible fusion pass * Update lists for pass * Add support for Pow operator * Add support for more activation types * Style * Rename fusion pass * First version of tests * Dirty version of pass * Polished version * Update pbtxt * Style * Update names * Style * Use PADDLE_ENFORCE_EQ * Save error message to variable * WO for error checks * CR * Static style check * Add missing 'activation_scale' attribute * Add relu6 and sigmoid activations * Style * Fix fuse list formating * Sync filenames for fuse pass files * Fix cmake after move * Fix registration * Fix pass name in tests * Add missing activations to checker * WIPS * Working mul op * Working sub * Working Add * Remove pten includes * Remove some forward declarations * Remove Includes * Fixes * Remove default kernels * Add check if post_ops attributes are avaliable * Style * Code adjustment * Register default kernels * We have year 2022 not 2021... Co-authored-by: Njakpiase <jakpia21@gmail.com> Co-authored-by: NSylwester Fraczek <sylwester.fraczek@intel.com> * Fast review fixes Co-authored-by: Njakpiase <jakpia21@gmail.com> Co-authored-by: NSylwester Fraczek <sylwester.fraczek@intel.com> * Review Fix * Rename one_dnn -> onednn * Style after review * Fast and dirty fix for quantization * Update tests * Style * Fix mkldnn_quantizer config * Add Joanna's suggestion. * Check if operator is explicitly disables on OneDNN * Try to use unregistered attributes * Style * Test new framework * FXI * FXII * Update test * Style Co-authored-by: Njakpiase <jakpia21@gmail.com> Co-authored-by: NSylwester Fraczek <sylwester.fraczek@intel.com>
-
- 09 3月, 2022 1 次提交
-
-
由 feng_shuai 提交于
-
- 07 3月, 2022 1 次提交
-
-
由 JingZhuangzhuang 提交于
* fix_conv2d_trt_convert_test_case * fix_conv2d_trt_convert_test_case * fix_conv2d_trt_convert_test_case * fix_conv2d_trt_convert_test_case
-
- 04 3月, 2022 1 次提交
-
-
由 ceci3 提交于
[paddle-inference]support setting fully connected in multi-head attention static shape branch to int8 (#39660) * fix inference int * update * add unittest
-
- 03 3月, 2022 2 次提交
- 01 3月, 2022 1 次提交
-
-
由 wenbin 提交于
* remove * pass * more pass
-
- 25 2月, 2022 1 次提交
-
-
由 jakpiase 提交于
-
- 23 2月, 2022 1 次提交
-
-
由 baoachun 提交于
* update gather_nd trt converter ut * update ut
-
- 22 2月, 2022 3 次提交
-
-
由 feng_shuai 提交于
* delete gather_ut skip_case * add trt version limit
-
由 feng_shuai 提交于
-
由 feng_shuai 提交于
-
- 21 2月, 2022 1 次提交
-
-
由 YuanRisheng 提交于
* remove infershape and Xshape * add xshape * fix bugs when run ci * fix bugs when run ci * fix bugs when run infrt test * pass converage
-
- 17 2月, 2022 2 次提交
- 16 2月, 2022 1 次提交
-
-
由 zlsh80826 提交于
-
- 15 2月, 2022 3 次提交
-
-
由 feng_shuai 提交于
-
由 Leo Chen 提交于
* Replace GeLU plugin with TRT built-in layers for approximate GeLU * Add TensorRT built-in layer for nonapproximate GeLU
-
由 feng_shuai 提交于
-
- 14 2月, 2022 1 次提交
-
-
由 Sławomir Siwek 提交于
* mish unit tests * code format * remove unused imports * code format * remove hard-coded shape values * remove timeouts * remove timeouts v2 * restore timeouts
-
- 11 2月, 2022 3 次提交
-
-
由 Leo Chen 提交于
-
由 jakpiase 提交于
* added shape oneDNN kernel * removed unnecessary import from test * added skipping tests for GPU * refactoring * refactored shape kernel * added tests in new framework * removed one line * minor change * added newline at EOF * added formatting * added attributes as extra
-
由 JingZhuangzhuang 提交于
-
- 10 2月, 2022 1 次提交
-
-
由 wenbin 提交于
* mkldnn conv fix * definetion
-
- 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
-
- 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
-