1. 27 10月, 2022 1 次提交
    • L
      make all cpp tests dynamic linked to libpaddle.so [except windows] (#47088) · 2096448b
      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
      2096448b
  2. 26 10月, 2022 2 次提交
  3. 20 10月, 2022 1 次提交
  4. 18 10月, 2022 1 次提交
    • W
      Merge layernorm trt fuse (#46320) · 5e9f491e
      Wang Bojun 提交于
      * first version, accuracy corrected
      
      * disable debug print
      
      * use blockReduceSum in phi
      
      * add UT
      
      * add opCompat
      
      * code style
      
      * code refine
      
      * bug fix
      
      * code refine
      
      * test fix
      
      * bugfix
      
      * codesytle fix
      
      * code style
      
      * code-style
      
      * code-style
      
      * code-style
      5e9f491e
  5. 17 10月, 2022 1 次提交
  6. 16 10月, 2022 1 次提交
  7. 27 9月, 2022 1 次提交
  8. 22 9月, 2022 1 次提交
  9. 21 9月, 2022 1 次提交
    • Z
      Enable PaddleInference to use CINN. (#45009) · 3aa6bd57
      Zhen Wang 提交于
      * use cinn in the paddle inference
      
      * fix some cmake errors
      
      * Avoid division by zero in the arange_kernel.
      
      * Avoid dynamic ops.
      
      * Remove some useless codes.
      
      * Use OpTransInfo to encapsulate some codes used in the build_cinn_pass.
      3aa6bd57
  10. 07 9月, 2022 1 次提交
    • W
      Layernorm shift partition (#45736) · 960109af
      wenbin 提交于
      * first commit
      
      * conver done
      
      * correct format
      
      * layernorm_shift_partition
      
      * correct convert
      
      * redefine plugin
      
      * runable
      
      * bug fix
      
      * modify ShiftPartitionPattern
      
      * correct
      
      * add UT
      
      * modify ut
      
      * compile
      
      * modify enforce
      
      * modify UT
      960109af
  11. 31 8月, 2022 1 次提交
  12. 30 8月, 2022 1 次提交
  13. 22 8月, 2022 2 次提交
  14. 16 8月, 2022 1 次提交
    • F
      convert multihead to oss (#45019) · f706d95d
      feng_shuai 提交于
      * convert multihead to oss
      
      * fix:bug
      
      * fix:delete const cast
      
      * fix:don't support bias_qk
      
      * add vit pass
      
      * fix:convert bug and add preln_residual_bias
      
      * support length=-1
      
      * add UT for convert
      
      * add no_bias_qk support for gpu_multihead_op
      
      * delete infer_shape depends on bias_qk
      
      * oss just can be used in T4 and A*
      
      * fix:change api for ROCM CI
      f706d95d
  15. 15 8月, 2022 1 次提交
  16. 05 8月, 2022 1 次提交
  17. 04 8月, 2022 1 次提交
    • S
      Matmuls with activation and elementwise_add fuses (#44655) · 0420d514
      Sławomir Siwek 提交于
      * Add unit tests
      
      * matmul_v2 + activation
      
      * matmuls + elementwise_add
      
      * matmul_v2 postops
      
      * transform matmul to v2
      
      * opcompat
      
      * fix fusing matmul with multipe outs
      
      * add shape constraints
      
      * remove unused vars
      
      * change pass order
      
      * - Unit tests to be debugged
      
      - fix
      
      - refactor
      
      - diagnostic
      
      - more diagnostic
      
      - fix
      
      - Fix number two
      
      - fix
      
      - fix
      
      - fix
      
      - alpha added
      
      - more fixes
      
      - compilation fix
      
      - removed diagnostic code
      
      - cosmetic fixes
      
      * lint
      
      * add alpha constraint
      
      * merge matmul refactor
      
      * trigger CI
      
      * - fix
      
      * - another fix
      
      * code style
      
      * add support for matmul+elementwise_add+activation
      
      * code style
      
      * fix bfloat16 bugs
      
      * change append_binary to append_sum
      Co-authored-by: NJacek Czaja <jacek.czaja@intel.com>
      0420d514
  18. 26 7月, 2022 2 次提交
  19. 12 7月, 2022 1 次提交
    • S
      matmul+activation fuse pass (#43519) · 3333a439
      Sławomir Siwek 提交于
      * add method for post ops
      
      * format code
      
      * gpd
      
      * format style
      
      * add matmul+act test
      
      * implement matmul+activation
      
      * whitespaces
      
      * code style
      
      * python code format
      
      * Increase UT timeout
      
      * code format
      
      * update style
      
      * generalize activation fuse passes
      
      * change order
      
      * Unify activation GPD
      
      * Revert changes with op_act
      
      * remove softmax mkldnn attrs
      
      * set common name for act attributes
      
      * whitespace
      
      * append postops by helper function
      
      * ut style
      
      * revert changes related to quantization
      
      * Reduce redundancy
      
      * reduce number of parameters
      
      * trigger CI
      
      * validate attribute
      
      * trim unit test
      3333a439
  20. 07 7月, 2022 1 次提交
  21. 04 7月, 2022 1 次提交
  22. 24 6月, 2022 1 次提交
  23. 23 6月, 2022 1 次提交
    • S
      [external reviewing] Params to int8 pass (#42625) · b8b2d6a9
      Sylwester Fraczek 提交于
      * sylwek
      
      prototype params to int8 pass
      
      * trying to make warmup work
      
      * wip
      
      * wip
      
      * change test to cpp test
      
      * review fixes, refactoring
      
      * more refactoring
      
      * add erasevars
      
      * change test to fixture
      
      * rename pass
      
      and reorder erasevars and graphsaferemovenodes
      
      * fix
      
      * more refactoring and fixed bug
      
      * formatting
      
      * remove scale count
      
      * enfroce message too short
      
      * remove erasevars
      
      erasevars couldbe cauuse of memory issues
      
      some other fixes
      
      * add count of successfull fuses to name of new nodes
      
      * FindVar -> GetVar and use ConvResidual pattern
      
      * use tensor->clear() instead of new variable
      
      * Update paddle/fluid/framework/ir/mkldnn/params_quantization_mkldnn_pass_tester.cc
      Co-authored-by: NTomasz Socha <tomasz.socha@intel.com>
      
      * Update paddle/fluid/framework/ir/mkldnn/params_quantization_mkldnn_pass_tester.cc
      Co-authored-by: NTomasz Socha <tomasz.socha@intel.com>
      
      * Update paddle/fluid/inference/tests/api/analyzer_lexical_analysis_gru_tester.cc
      Co-authored-by: NTomasz Socha <tomasz.socha@intel.com>
      
      * add log (review fix)c
      
      * review fix (2 functions to one)
      
      * code review: Conv->QuantizeConv
      
      * revert
      
      * fix formatting
      
      * remove unused functions
      
      * add paddle enforce
      Co-authored-by: NTomasz Socha <tomasz.socha@intel.com>
      b8b2d6a9
  24. 20 6月, 2022 1 次提交
  25. 13 6月, 2022 1 次提交
  26. 09 6月, 2022 1 次提交
  27. 04 6月, 2022 1 次提交
  28. 02 6月, 2022 1 次提交
  29. 19 5月, 2022 1 次提交
  30. 17 5月, 2022 1 次提交
  31. 13 5月, 2022 1 次提交
  32. 12 5月, 2022 1 次提交
  33. 11 5月, 2022 1 次提交
    • Z
      Move weights and biases scale computing into pass (#42241) · c0652972
      Zuza Gawrysiak 提交于
      * Add int8 scales gathering pass for convolution
      
      * Fix typo
      
      * Add unittest
      
      * Add corrected unit test
      
      * Change test name
      
      * Remove enabling mkldnn in test
      
      * Speed up test
      
      * Change max examples
      
      * Add functional test
      
      * Change test name
      
      * Add new test case
      
      * Rename pass
      c0652972
  34. 10 5月, 2022 1 次提交
    • P
      Rea-dd conv_affine_channel fuse pass as oneDNN only pass (#41998) · 3540d33b
      piotrekobi 提交于
      * Readd conv_affine_channel fuse pass as mkldnn pass
      
      * Fix formatting
      
      * Add new test to parallel_UT_rule.py
      
      * Fix Coverage and Windows CI issues
      
      * Revert "Fix Coverage and Windows CI issues"
      
      This reverts commit f33459846385c9fd51c07f9f44e7ff283a652637.
      
      * Fix CI errors
      
      * Remove unnecessary conv_eltwise_add_affine_channel fuse pass
      
      * Remove test from parallel_UT_rule.py
      3540d33b
  35. 06 5月, 2022 1 次提交
  36. 27 4月, 2022 1 次提交
  37. 14 4月, 2022 1 次提交
    • S
      FC+elementwise_add (residual connection) (#41776) · 92d8d0bc
      Sławomir Siwek 提交于
      * Change tensor name to match activation
      
      * declare fc_eltwise_add pass
      
      * merge conv_eltwise refactor PR
      
      * first compilable draft
      
      * unittest feedback tools
      
      * Fuse pass tester
      
      * Move IsReachable() to shared file
      
      * 100% coverage of fuse_pass_tester.cc
      
      * register pass
      
      * Add bias node
      
      * Improve unit tests / remove bias node from pattern
      
      * improve fc_eltwiseadd_unittest
      
      * cancel eltwise_add fuse if act is already fused
      
      * Add elementwise_input scale
      
      * Residual MVP
      
      * Add new FC attrs
      
      * Add more test cases
      
      * Add missing op attrs
      
      * Adapt code to new Elementwise pattern
      
      * reuse existing fcpattern
      
      * improve code style
      
      * remove unused arguments
      
      * fix typo
      
      * remove whitespace
      
      * remove int8 related code
      
      * Remove attributes from base ops
      
      * style
      
      * style check
      
      * Remove input from base op
      
      * Set attribute during fuse
      
      * ut timeout
      
      * download and test model
      
      * DRY
      
      * apply feedback from review
      
      * Style check
      
      * fix typo
      
      * cosmetic changes
      
      * explicitly set residual as output
      
      * VIT-OCR accuracy check
      
      * trigger CI
      
      * remove whitespaces
      
      * fix missing data file
      92d8d0bc