- 12 10月, 2022 11 次提交
-
-
由 Weilong Wu 提交于
-
由 zhoutianzi666 提交于
-
由 Leo Chen 提交于
* refactor * refine code
-
由 Wangzheee 提交于
-
由 weishengying 提交于
-
由 zyfncg 提交于
-
由 sneaxiy 提交于
* fix some ops for int64 range * update error message
-
由 zhouweiwei2014 提交于
* [Zero-Dim] support input 0D Tensor for unary api * fix CI
-
由 sunli 提交于
* optimize cinn subgraph detector * fix update subgraph * add annotation
-
由 Shuangchi He 提交于
-
由 niuliling123 提交于
-
- 11 10月, 2022 22 次提交
-
-
由 Wangzheee 提交于
* add_lookup_table_v2
-
由 Sylwester Fraczek 提交于
* add logging to fc residual fuse pass * expand logging message to fc residual fuse pass * Add test for fc residual not fusing with activation
-
由 Wen Sun 提交于
-
由 Wen Sun 提交于
-
由 Chenxiao Niu 提交于
-
由 Chenxiao Niu 提交于
-
由 Leding Li 提交于
* Add missing <cstddef> * Fix some iterator type * Currently use host protobuf to bypass build failure
-
由 Aganlengzi 提交于
-
由 Wangzheee 提交于
-
由 Chen Weihang 提交于
* remove using lodtensor part1 * polish history code format
-
由 yeliang2258 提交于
* fix slice bugs * fix * update code * fix * update code
-
由 HongyuJia 提交于
-
由 HongyuJia 提交于
* refine conv_op mkldnn code * fix customized_type_value
-
由 HongyuJia 提交于
* refine sum_op mkldnn code * refine sum_op mkldnn code
-
由 HongyuJia 提交于
-
由 Weilong Wu 提交于
-
由 傅剑寒 提交于
* add fp16 data type for set_value * cancel flip modification * add fp16 dtype support for set_value
-
由 HongyuJia 提交于
* solve transpose2, follow #22402 * fix CI cmake * update REGISTER_OP_KERNEL of transpose2
-
由 HongyuJia 提交于
-
由 Zhen Wang 提交于
* Fix some bugs hidden in build_cinn_pass. * Update codes about OpTransInfo. * Only support for the static reshape/reshape2 op.
-
由 niuliling123 提交于
-
由 wuyefeilin 提交于
-
- 10 10月, 2022 7 次提交
-
-
由 Tony Cao 提交于
* Update README.md * Update README.md * Fix F541 by converting f-string to normal strings
-
由 YuanRisheng 提交于
* add yaml entry for rnn and rrnn_grad, move infershape function for rnn_grad to phi infer meta * WIP: move rnn kernrl to phi * Change the code generation to avoid converting from intializer list to tuple of heterogeneous types. This is only triggered when an api has intermediate outputs, and the result of the outputs are of heterogeneous types. * fix the bug that when none in a vector of tensors requires gradient, the conversion to InferShapeContext to InferMetaContext (a.k.a. BuildInferMetaContext) produces errorous results. * fix ci bugs * fix ci bugs * fix ci bugs * modify code according comment Co-authored-by: Nchenfeiyu <chenfeiyu@baidu.com>
-
由 Leo Chen 提交于
* reduce time cost on atomic in interpretercore * clear code of PrepareAtomic in interpretercore * refine threadpool cache
-
由 Zhang Jun 提交于
-
由 Sylwester Fraczek 提交于
* fix fc pattern remove use_bias add residual input switch fix references to pattern * review fixes
-
由 Sylwester Fraczek 提交于
* Add methods that find input or output name by var name * kind of bugfix - initialize variables * ci fix * review fixed
-
由 zhoutianzi666 提交于
-