1. 20 2月, 2022 1 次提交
  2. 19 2月, 2022 1 次提交
    • A
      [Pten]Unify paddle/pten::framework::ddim into pten::ddim (#39614) · 2fe04264
      Aurelius84 提交于
      * Unify paddle/pten::framework::ddim into pten::ddim
      
      * fix paddle namespace
      
      * compile sucessfully
      
      * fix npu src file
      
      * fix conflict
      
      * fix conflict
      
      * fix tensorrt compiler error
      
      * fix conflict
      
      * fix conflict
      
      * fix tesst file conflict
      
      * fix conflict
      
      * fix mlu file conflict
      
      * fix mlu file conflict
      
      * fix cinn header file conflict
      
      * fix conflict
      
      * fix conflict
      
      * fix conflict
      
      * fix conflict
      2fe04264
  3. 18 2月, 2022 1 次提交
  4. 15 2月, 2022 2 次提交
    • F
      [Pten] move paddle/operators/math/functors.h and compound_functors.h (#39514) · 0d46a108
      Feiyu Chan 提交于
      * move paddle/operators/math/functors.h
      * move paddle/operators/math/compound_functors.h
      0d46a108
    • A
      [PTen]Migrate proto::VarType outside of Pten (#39411) · 7e7e9404
      Aurelius84 提交于
      * #1 migrate dist-related type()-> dtype()
      
      * move datatype function from pten -> fluid/framework
      
      * change type() in imperative into convert(dtype())
      
      * modify xx_tensor->type into xx_tensor->dtype
      
      * change the set_type interface and the caller
      
      * modify xx_tensor.type into xx_tensor.dtype
      
      * fix mutable_data(place, dtype())
      
      * change caller of mutable_data in pten and distributed
      
      * change the caller of mutable_data in fluid/framework
      
      * change the caller of mutable_data in imperative directory
      
      * mutable_data: inference
      
      * update the call of mutable_data
      
      * transfer MakePenScalarArray MakePtenScalar ResetHolderWithType
      
      * pass the compile. the next step is remove VarType in Pten
      
      * fix all and remove VarType from pten. success in linux. Next task is other platform
      
      * fix conflict with develop
      
      * fix compiled error
      
      * Fix reset conversion
      
      * fix conflict
      
      * fix compiled problem
      
      * fix typo
      
      * Fix << in tensor_utils.cc
      
      * fix type->dtype
      
      * fix unittest
      
      * fix tensor init constructor
      
      * fix DataTypeSize for BFloat16
      
      * fix code style
      
      * fix npu compiled error
      
      * fix npu
      
      * compile npu sucessfully
      
      * fix conflict
      
      * fix conflict
      Co-authored-by: Nxiongkun <xiongkun03@baidu.com>
      7e7e9404
  5. 11 2月, 2022 1 次提交
  6. 08 2月, 2022 1 次提交
  7. 06 2月, 2022 1 次提交
  8. 29 1月, 2022 1 次提交
    • L
      Optimize layer norm backward cuda kernel when cols is 1024. (#39247) · 99cfcc09
      Li Min 提交于
      * Add fp16 support for scale/bias for fused_layernnorm_residual_dropout_bias op.
      
      * Remove useless code.
      
      * Remove useless code.
      
      * Optimize layer_norm fwd when cols is 1024.
      
      * Remove useless code.
      
      * Minors.
      
      * Minors.
      
      * Modifications accordding to reviews.
      
      * Minors.
      
      * Optimize layer_norm bwd kernel when cols is 1024.
      
      * Polish layer_norm_bwd_1024 kernel.
      
      * Limit ln_bwd_1024_kernel to paddle_with_cuda.
      
      * Fix double type compile error.
      
      * Add optimization of ln bwd for fused_dropout_add_ln op.
      
      * Polish codes.
      99cfcc09
  9. 26 1月, 2022 2 次提交
    • L
      [pten] remove deprecated fluid op kernel for pten (#38842) · 3ab9aef1
      Leo Chen 提交于
      * update cmake file to remove fluid kernel
      
      * add pten declaration.h to where pybind.h used
      
      * fix sync_bn and tensorrt_engine
      
      * refine detection_library
      
      * fix interpreter_core
      
      * support eager legacy
      
      * fit eager legacy for pten
      
      * fall back to cpu if not found kernel
      
      * fix compile problem
      
      * fix compile problem
      
      * refine fallback logic
      
      * fit operator.run()
      
      * fix xpu compile
      
      * fit for new_exec
      
      * add REGISTER_OP_WITHOUT_GRADIENT
      
      * un-cache pt_kernel_context
      
      * fix compile
      
      * fix cudnn
      
      * fix compiling with on_infer
      
      * fix mkldnn
      
      * fix isfinite_v2
      
      * fix xpu problem
      
      * fix op_device
      
      * refine fallback for xpu
      
      * fix xpu compile
      
      * merge develop
      
      * refine code format
      
      * fix compile
      
      * fix compile
      
      * add data_transfer
      
      * fix PreparePtenData
      
      * fix cpu context
      
      * merge develop
      
      * fix compile
      
      * fix error device context
      
      * fix xpu
      
      * fix dev_ctx
      3ab9aef1
    • L
      Optimize layer norm forward when cols is 1024. (#39167) · 01d04be6
      Li Min 提交于
      * Optimize layer_norm fwd when cols is 1024.
      01d04be6
  10. 25 1月, 2022 1 次提交
    • W
      [Move selected_rows PR #3] Change the relationship of [include/Cmake]. (#39128) · 2bafd338
      Weilong Wu 提交于
      * Added selected_rows and rw_lock to pten
      
      * Renamed the unit test target to fix CI
      
      * Removed Class SelectedRows in Fluid, changed include/cmake relationship, use pten::SelectedRows in Fluid
      
      * Remove rw_lock.h,rw_lock_test.cc in fluid
      
      * Use pten::RWLock and pten::AutoRDLock, fix CI
      
      * Use pten::SelectedRows
      
      * Use pten::SelectedRows
      
      * Fix to pass NPU CI
      
      * Use pten::SelectedRows, to pass NPU CI
      
      * To fix NPU CI
      
      * To fix NPU CI again
      2bafd338
  11. 24 1月, 2022 1 次提交
  12. 21 1月, 2022 1 次提交
  13. 18 1月, 2022 1 次提交
  14. 17 1月, 2022 1 次提交
    • W
      [Pten] Replace platform::Place to pten::Place. (#38899) · c48a9ad5
      Wilber 提交于
      * add pten::Place data structure.
      
      * update ci problem
      
      * fix ci problem
      
      * update
      
      * using platform::Place=pten::Place
      
      * remove BOOST_GET_CONST for CPUPlace and GPUPlace
      
      * compile pass 25%.
      
      * compile pass 45%
      
      * compile pass 60%
      
      * remove boost_get for xpu npu mlu and ipu
      
      * compile pass on cpu and gpu.
      
      * fix compile problem
      
      * fix compile error.
      
      * update
      
      * fix ci problem
      
      * update
      
      * ci approve
      
      * fix ci problem
      
      * fix ci eager test problem
      
      * remove BOOST_GET_CONST
      
      * fix npu compile
      c48a9ad5
  15. 12 1月, 2022 1 次提交
    • L
      Adjust warpper of gpu_lanuch_config (#38654) · f5166284
      limingshu 提交于
      * first commit
      
      * fix wrong filename
      
      * fix the wrong spell name
      
      * fix gpu config warper
      
      * modify according to pr advices
      
      * fix GpuLauchConfig1D api bugs
      
      * change the config for dropout grad
      
      * fix bugs
      
      * modification according to pr advices
      
      * modification according to pr advices
      f5166284
  16. 07 1月, 2022 1 次提交
  17. 28 12月, 2021 1 次提交
  18. 24 12月, 2021 1 次提交
    • C
      [pten] combine reduce_cuda codes (#38328) · 08941eda
      chentianyu03 提交于
      * combine reduce_cuda codes
      
      * support float16 in pten redcue_mean
      
      * replace ReduceCudaKernel impl with pten reduce impl
      
      * mv reduce funcs into reduce_cuda_impl
      
      * rm unsed codes and headers
      
      * mv GetReduceDim into reduce_cuda_impl
      
      * recover GetReduceDim in reduce_op.h
      
      * add new dispatch macro
      
      * fix pool op output not inited and cause transform to pten::denseTensor error
      
      * fix output tensor not initialized error
      
      * rename new dispatch macro and format code style
      
      * rm reduce_functor_op.h file
      08941eda
  19. 17 12月, 2021 1 次提交
  20. 16 12月, 2021 1 次提交
  21. 03 12月, 2021 1 次提交
  22. 29 11月, 2021 1 次提交
  23. 23 11月, 2021 1 次提交
  24. 19 11月, 2021 1 次提交
    • W
      Add fuse_resnet_unit pass (#36818) · 3cd3bf29
      wuhuanzhou 提交于
      * GeneratePass support attr condition and mapping, test=develop
      
      * fix coverage, test=develop
      
      * Add fuse_resnet_unit pass, test=develop
      
      * fix CI errors, test=develop
      
      * fix CI errors, test=develop
      
      * fix unittest error when compiling without CUDA, test=develop
      
      * fix static ci error, test=develop
      
      * limit kernel size must equal 1, test=develop
      3cd3bf29
  25. 17 11月, 2021 1 次提交
  26. 16 11月, 2021 1 次提交
    • L
      Fix attn_bias_add bug. (#37147) · a9e7a854
      Li Min 提交于
      fused_attention_op的实现中,使用了bias_add,且其实现是通过使用kernel primitive来实现的,之后kernel primitive的WriteData api接口及函数内部实现发生了更改,将判断越界的逻辑移到了template的参数中,使得调用的分支有错误,产生了越界赋值操作,污染了别的显存空间的内容。具体表现为:test_fused_attention_op_api.py 单次执行基本上不会报错,多次循环执行不同shape的输入,结果计算不对,具有偶发性,bug不易察觉。
      a9e7a854
  27. 12 11月, 2021 1 次提交
  28. 10 11月, 2021 1 次提交
  29. 08 11月, 2021 1 次提交
  30. 05 11月, 2021 1 次提交
    • J
      Disable pool&conv_transpose&quantize caching (#36695) · db6c00c4
      Jacek Czaja 提交于
      * - WIP
      
      - compilation fix
      
      - fix
      
      - fixes
      
      - fix
      
      - fix
      
      - fix again
      
      - fix
      
      - another fix
      
      - another compilation fix
      
      - fix
      
      - fix
      
      - fix
      
      - lint
      
      * - pool2d partially stripped from cache
      
      - pool2d partially stripped of caching
      
      * - compilation fix
      
      * - compilation fix
      
      * - Fix to UT of caching
      
      * - Enabling test_conv3d_mkldnn
      
      * - conv_transpose stripped of cache
      
      * - compilation fix
      
      * - fix
      
      * - fix
      
      * - compilation fix
      
      * - fix
      
      * Reverted disabling caching of conv2d
      
      * - compilation fix
      
      * - ut reverted
      db6c00c4
  31. 28 10月, 2021 1 次提交
  32. 26 10月, 2021 2 次提交
    • L
      Add fused attention op backward and python layer. (#36498) · 5119428e
      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;
      5119428e
    • L
      Move fused_attention and fused_feedforward functional api path to incubate (#36704) · 9aeca2f1
      Li Min 提交于
      将 #35905 和 #35843 PR中新增的的python api接口移到incubate目录下。
      9aeca2f1
  33. 25 10月, 2021 2 次提交
    • Z
      add op: fused_feedforward(backward) (#35611) · 2dd0a46a
      zhangkaihuo 提交于
      这个PR是fused_feedforward反向的代码
      
      相关kernel实现:fused_dropout_act_bias, fused_residual_dropout_bias, fused_layernorm_residual_dropout_bias
      
      fused_feedforward是一个融合算子,该算子对transformer模型的feed forward层的算子进行融合和封装,使得前端只呈现一个接口,通过融合减少部分访存和kernel launch的时间,以此提升性能。
      2dd0a46a
    • Z
      add op: fused_feedforward(forward) (#35843) · b18cbfb2
      zhangkaihuo 提交于
      这个PR只包含fused_feedforward前向的代码。
      
      相关kernel实现:fused_dropout_act_bias, fused_residual_dropout_bias, fused_layernorm_residual_dropout_bias
      
      fused_feedforward是一个融合算子,该算子对transformer模型的feed forward层的算子进行融合和封装,使得前端只呈现一个接口,通过融合减少部分访存和kernel launch的时间,以此提升性能。
      b18cbfb2
  34. 22 10月, 2021 1 次提交
    • L
      Fused attention op forward (#35905) · d4906214
      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
  35. 21 10月, 2021 1 次提交
  36. 15 10月, 2021 1 次提交