Skip to content

P
Paddle

PaddlePaddle / Paddle
大约 1 年 前同步成功

通知 2298
Star 20931
Fork 5422
P
Paddle
切换分支/标签
  1. 26 10月, 2021 18 次提交
  3. 25 10月, 2021 12 次提交
  5. 24 10月, 2021 1 次提交
  7. 23 10月, 2021 6 次提交
    • J
      add cinn graph symbolization (#36417) · bbd4bd73
      由 jiangcheng 提交于 
      * add cinn graph symbolization

* fix some bug

* add paddle scope to cinn scope

* add paddle scope to CINN scope in Symbolization, and add feed op when build cinn pass

* fix some bug

* fix some bug by review advices

* optimize code problem

* revert build_cinn_pass and move the change to https://github.com/PaddlePaddle/Paddle/pull/36503

* fix some bug after co-compilation

* perfect single test script

* remove scope and rename feed_target to input_tensor

* using std::unordered_map instead of absl::flat_hash_map

* fix single test bug

* revert to preverion for WITH_CINN has add in later PR

* full error information for CI

* full enfore information for CI pass
      bbd4bd73
    • W
      disable padding if dynamic shape (#36648) · 99e396f8
      由 wenbin 提交于 
      * disable padding if dynamic shape

* add parentheses

* correct
      99e396f8
    • B
      fix interpolate mkldnn op error (#36623) · f6d82526
      由 baoachun 提交于
      f6d82526
    • W
      add file exists check (#36628) · 425db7c8
      由 Wilber 提交于 
      * add file check

* add ut
      425db7c8
    • J
      Add transformer of paddle desc and cinn desc (#36100) · 3cb6f65e
      由 jiangcheng 提交于 
      * add transformer of paddle desc and cinn desc

* change LOG(FATAL) to PADDLE_THROW for ci

* full error imformation for ci

* fix some problem as review advice

* fix some bug

* move vat type utils to tansform_desc header file

* add if NOT WITH_CINN control whether compile

* build_strategy check whether open WITH_CINN

* add control WITH_CINN in cmake
      3cb6f65e
    • H
      New Paddle-CINN Compile PR (#36584) · ab732884
      由 Huihuang Zheng 提交于 
      This PR added some changes to match the CINN change for compilation. It also tried to fix JiangCheng's Problem in PR: https://github.com/PaddlePaddle/Paddle/pull/36100

These changes include:
1. Set `CINN_GIT_TAG` to a newer tag
2. CINN now just `make cinnapi -j`
3. We have to add `-DPY_VERSION=${PY_VERSION} -DWITH_TESTING=ON` to CINN cmake args
4. For CINN's third party dependencies, we could just include headers without target_link_libraries
5. Moved `cinn.cmake` from `paddle/cmake` to `paddle/cmake/external` to match old style. External folder contains `lite`, which is the same level of `cinn`
6. CINN added `-DNAMESPACE=cinn_gflags` in `gflags.cmake` to have different gflag namespaces between CINN and Paddle. It solved re-define problem.
7. Change namespace of `::google::` in gflags to `::GFLAGS_NAMESPACE`
      ab732884
  9. 22 10月, 2021 3 次提交
    • W
      correct slice serialize data (#36588) · 5e880840
      由 wenbin 提交于 
      * slice

* add UT
      5e880840
    • Z
      add fp16 kernel for clip_op (#36577) · 1962d3af
      由 zhangbo9674 提交于
      1962d3af
    • L
      Fused attention op forward (#35905) · d4906214
      由 Li Min 提交于 
      功能：本PR的目标是提高attention模块的计算性能。
为了减少框架层对op的调度开销，本PR通过在C++层手动实现attention模块，对外提供attention 大op；
为了减少防存开销，本PR采取了两种优化方法：
（1）在q,k,v计算时通过共享输入X，将该处的gemm，transpose和bias add从三次调用减少为一次；
（2）使用kernel融合优化技术，在不同cuda kernel之间通过寄存器传输数据；
      d4906214