Skip to content

P
Paddle

PaddlePaddle / Paddle
1 年多 前同步成功

通知 2302
Star 20931
Fork 5422
P
Paddle
切换分支/标签
  1. 11 3月, 2022 4 次提交
  3. 10 3月, 2022 3 次提交
  5. 09 3月, 2022 12 次提交
  7. 08 3月, 2022 11 次提交
  9. 07 3月, 2022 9 次提交
    • X
      [OpTest] Support to test paddle API end-to-end for check_eager (#40169) · 79a32715
      由 xiongkun 提交于 
      * add python api test in TestOp

* test_python_api if self.python_api is set

* fix code by CR
      79a32715
    • H
      refactor unittest for nearest_interp_v2_op_xpu. test=kunlun (#39804) · c09adab8
      由 houj04 提交于 
      * refactor unittest for nearest_interp_v2_op_xpu. test=kunlun

* fix code style. test=kunlun

* fix code style. test=kunlun
      c09adab8
    • M
      cuBlasLt Epilogue To Fuse Linear + ReLU|GeLU (#39437) · 2a3d9eca
      由 Ming-Xu Huang 提交于 
      * Added cuBlasLtHandle_t to device context.

* Added fused_gemm_epilogue op.

1. Added fused_gemm_epilogue op to leverage cuBlastLt Epilogue.
2. Support fusion Act(X*Y + bias), X'dims >=2 and Y'dims shoule be 2.
2. Act currently only be supported ReLU. (Will add GeLU in the future).

* Added UT to fused_gemm_epilogue op.

* Added LinearAct Pattern

1. Added LinearAct into graph_pattern_detector.* to define (2.)'s
pattern.
2. LinearAct is used to detect act(element_add(matmul_v2(x, w), bias)).
3. act currently only support ReLU (Will support GeLU in the future).

* Added FuseGemmEpiloguePass

1, Added FuseGemmEpiloguePass to handle nn.Linear + Act{ReLU}
fusion (GeLU will be supported in the future).
2. Only support matmul_v2 from nn.Linear.

* Added pybind to BuildStrageter.fuse_gemm_epilogue_.

* Added UT for fuse_gemm_epilogue_pass.

* GeLU support and EpilogueSingleton

1. Added GeLU support to fused_gemm_epilogue op.
2. Added EpilogueSingleton to cache auxiliary pointer.
3. Added related UTs.

* Rename cublaslt_epilogue_opto gemm_epilogue_op.*.

* Added both train and infer pattern to LinearAct.

1. Added support of fwd graph with grap_ops linking to LinearAct.
2. Added related changes to fuse_gemm_epilogue_pass for above
modification.

* Changed CUDA requirement from 11.4 to 11.6 for fuse_gemm_epilogue_pass.

* Added identity activation support to gemm_epilogue_op.

* Added Linear Fusion (matmul_v2 + ele_add)

1. Added matmul_v2 + ele_add pattern to LinearActPattern.
2. Added matmul_v2 + ele_add support to fuse_gemm_epilogue_pass.

* Rename gemm_epilogue_op.* to fused_gemm_epilogue_op.*

* Add fused_gemm_epilogue_grad op.

1. Added fused_gemm_epilogue_grad to support backward epilogue fusion.

* Add UTs to fused_gemm_epilogue_grad_op.

* Change attribute name in fused_gemm_epilogue_grad_op for clearing.

* Allow DX and DBias be dispensable to fused_gemm_epilogue_grad op.

* Added ElementwiseAdd+Matmul+Act graph pattern detection.

* Fuse backward of Linear( Act(x))

1. Added backward fusion pass to Linear( Act(x)).
2. Added backward fusion pass to Linear(x).

* Added UTs to backward fusion of Linear(Act(x)).

* Complete document of arguments to fused_gemm_epilogue_op.

* Made arguments of some functions pass by reference.

* Modify code with review comments.

1. Made arguments of some function pass by reference.
2. Removed redundant code.
3. Followed Google code style to change code.

* Made 'const' code style be consistent

* Fixed random seed of python UTs.

* Set Compiling constrains to cuBlasLt

1. Require CUDA 11.6+
2. Remove fuse_gemm_epilogue related tests when CUDA < 11.6.

* Code Reivew from Paddle

1. Changed arguments name is_first_gemm to without_x_gradient for
clearing.
2. Applied PADDLE_THROW in fused_gemm_epilogue_op.

* Remove EpilogueSingleton

1. Applied ReserveSpace to replace Epilogue for passing auxiliary
pointers between FWD and BWD.

* Fix a logical error and enhance UTs.

1. Added act op count checking in UTs.
2. Fix issue to fuse backward or ReLU(Linear(X)).
3. TODO: solve GELU fusion issues.

* Fix Linear and GeLU fusion issues.

1. Modified graph_detech_pattern to fit with both linear wiht gelu or
relu.
2. Modified data range in Uts to allow negative values.

* Removed fused_gemm_epilogue_op.h.

* Rename namespace pten to phi.

* Rename name of arguments in fused_gemm_epilogue_op

1. bias -> Bias.
2. out -> Out.
3. reserve_space -> ReserveSpace.

* Change EpiloguePassActivationCache as local variable.

1. Removed singleton in EpiloguePassActivationCache.
2. Made EpiloguePassActivationCache as an argument to each pass
functions.
      2a3d9eca
    • J
      fix_conv2d_trt_convert_test_case (#39882) · d255bfe0
      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
      d255bfe0
    • Z
      [bf16] add bf16 kernel: gaussian_random fill_constant fill_any_like (#40027) · 6a0d60d2
      由 zhangbo9674 提交于 
      * add gaussian random

* add full

* refine reduce

* refine code

* refine gaussian_random unittest

* add unittest for fill_any_like fill_constant
      6a0d60d2
    • Z
      [AutoParallel]engine support pp (#40084) · 71cb016c
      由 zhaoyingli 提交于 
      * engine support pp

* fix format

* avoid multi print

* fix convert

* bug fix

* add pp unittest
      71cb016c
    • Z
      [bf16] add bf16 kernel: sigmoid & sqrt & softplus & square (#40004) · 98c427e2
      由 zhangbo9674 提交于 
      * add activ

* refine unittest

* refine unittest

* refine unittest

* refine unittest

* refine code
      98c427e2
    • L
      initialize processgroupnccl with store (#40181) · 0ad25fb9
      由 lilong12 提交于
      0ad25fb9
    • Z
      [AMP] refine paddle.amp.decorate code example (#40159) · da3de72d
      由 zhangbo9674 提交于 
      * refine amp.decorate code example

* refine code
      da3de72d
  11. 05 3月, 2022 1 次提交