- 10 11月, 2022 1 次提交
-
-
由 RichardWooSJTU 提交于
* add fuse_multi_transformer_layer_pass
-
- 09 11月, 2022 3 次提交
-
-
由 joanna.wozna.intel 提交于
-
由 Paulina Gacek 提交于
* Analysis API interface for disabling fc passes * Unit tests corrected * Python API added * test runs only when PADDLE_WITH_MKLDNN * Fc op changed to relu in matmul_op_test * Disable fc passes in tests where acc drops * code formating * Unit test for analysisConf added * Unit test gpu added * fc passes disabled when iterations=0 in gru test * style * passes disabled when fp32 in gru test * fc passes disabled in lstm test * Import from inference, not fluid in doc
-
由 Wangzheee 提交于
* upgrade scale and slice op convert for Paddle-TensorRT
-
- 08 11月, 2022 5 次提交
-
-
由 Wilber 提交于
-
由 Kaipeng Deng 提交于
-
由 zhoutianzi666 提交于
* allow fold fill_constant && allow nms3 into trt in int8 model * use unordered_map * fix CI failing
-
由 Paulina Gacek 提交于
* Split kernel registered, tests for uint/int added * Split quantized * Split output scales calculated only once * NearestInterp test fix reversed * DequantizeOutputs corrected
-
由 zhoutianzi666 提交于
* fix cast bug
-
- 07 11月, 2022 3 次提交
-
-
由 Hui Zhang 提交于
* suqeeze2 transpose2 fuse onednn * format * fix output shape * fix conflict * format * format * remove useless * remove log * simply pass * fix comment * fix * fix msg * fix error msg * format
-
由 Yuanle Liu 提交于
-
由 Qi Li 提交于
-
- 04 11月, 2022 2 次提交
-
-
由 shentanyue 提交于
-
由 jakpiase 提交于
* tmp save * minor chnage * CI fix * added FC optimizations * latest update * CI fix * fixed bug with fusing fc
-
- 03 11月, 2022 2 次提交
-
-
由 Wangzheee 提交于
* disable_lookup_table_v2
-
由 yeliang2258 提交于
* add constant_folding_pass pass for mkldnn int8 * update UpdateScaleOpInOutScales
-
- 02 11月, 2022 2 次提交
- 01 11月, 2022 4 次提交
-
-
由 Yuanle Liu 提交于
-
由 shentanyue 提交于
-
由 Nyakku Shigure 提交于
* [CodeStyle][E712] use `if cond`/`if cond is True` for comparison with `True` * revert changes in fluid * revert unrelated file * revert changes in norm * revert changes in auto_parallel_amp * fix norm and auto_parallel_amp * revert a typo fix due to fixed at #47477
-
由 shentanyue 提交于
-
- 31 10月, 2022 3 次提交
-
-
由 wanghuancoder 提交于
* fix predictor memory write overflow
-
由 feng_shuai 提交于
* feat: add int8 support for vit * test:add test
-
由 feng_shuai 提交于
* optimize: vit 384 * fix:bug * fix:bug * fix:supoort rocm complie * refactor:name * fix:support rocm * fix:__HIP_NO_HALF_CONVERSIONS__ * optimize: delete scalar * fix:rocm can't support * fix:ernie error
-
- 28 10月, 2022 2 次提交
-
-
由 Aurelius84 提交于
* [JITLayer]Enable OneDNN on CPU and Fix zero shape * remove VLOG
-
- 27 10月, 2022 5 次提交
-
-
由 Aurelius84 提交于
* add predictor_engine * add predictor_engine * fix zero shape * fix lodTensor * fix unittest * fix code style * update CmakeList
-
由 Yuanle Liu 提交于
-
由 Leo Chen 提交于
* make all cpp tests dynamic linked to libpaddle.so * add comments * keep old cc_test for some tests * fix some ut * make some ut use cc_test_old * fix typos and fit for win32 * fix lib path * fix some tests * skip lite test * fit for rocm * fit for cinn * fit for mac * fit for win32 * skip inference ut * skip windows * fix coverage
-
由 Zhen Wang 提交于
-
由 Chen Weihang 提交于
* fix compile error of mkldnn * fix tensorrt error
-
- 26 10月, 2022 3 次提交
-
-
由 wenbin 提交于
* prelnlayernorm_shift * add ut * remove paddle_enforce * remove useless * add UT * remove UT * add UT * set timeout
-
由 Sławomir Siwek 提交于
* fc/matmuls + scale fuse pass * remove double-extension * add unit tests * comments from review * codestyle * add pass to int8 list * new codestyle * attr name typo
-
由 Chen Weihang 提交于
* remove using lodtensor part2 * resolve code format error * resolve conflict * resolve conflict * replace added frameworrk tensor
-
- 25 10月, 2022 1 次提交
-
-
由 engineer1109 提交于
export all symbols for phi_function_api on paddle_inference_shared
-
- 24 10月, 2022 4 次提交
-
-
由 duanboqiang 提交于
-
由 feng_shuai 提交于
-
由 Wilber 提交于
-
由 Wang Xin 提交于
* fix macos inconsistent-missing-override warnings * fix inconsistent-missing-override error in test
-