1. 10 8月, 2022 1 次提交
  2. 05 8月, 2022 2 次提交
  3. 04 8月, 2022 3 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
    • Z
      [Paddle-TRT] add Rnn (#44678) · ffc8defa
      zhoutianzi666 提交于
      * add rnn
      ffc8defa
    • W
      convert support multi block. (#44866) · b4a4eef2
      Wilber 提交于
      * convert support multi block.
      
      * update
      b4a4eef2
  4. 02 8月, 2022 1 次提交
  5. 01 8月, 2022 3 次提交
  6. 29 7月, 2022 1 次提交
  7. 28 7月, 2022 1 次提交
  8. 26 7月, 2022 1 次提交
  9. 22 7月, 2022 1 次提交
  10. 21 7月, 2022 2 次提交
  11. 19 7月, 2022 3 次提交
  12. 18 7月, 2022 1 次提交
  13. 15 7月, 2022 1 次提交
  14. 13 7月, 2022 1 次提交
  15. 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
  16. 11 7月, 2022 2 次提交
  17. 08 7月, 2022 1 次提交
  18. 07 7月, 2022 1 次提交
  19. 30 6月, 2022 1 次提交
  20. 29 6月, 2022 2 次提交
  21. 28 6月, 2022 2 次提交
  22. 26 6月, 2022 1 次提交
  23. 24 6月, 2022 1 次提交
  24. 23 6月, 2022 2 次提交
    • C
      add cast trt converter (#43447) · b6bf8994
      ccrrong 提交于
      * add cast trt converter
      b6bf8994
    • 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
  25. 22 6月, 2022 2 次提交
  26. 21 6月, 2022 2 次提交
    • H
      [Inference]Fix the ort Backend multiple input bug (#43621) · 61591afe
      heliqi 提交于
      * fix or backend many inputs bug
      
      * fix or backend many inputs bug
      
      * fix or backend many inputs bug
      
      * fix or backend many inputs bug
      
      * code format
      
      * code format
      61591afe
    • S
      Generalize conv+activation fuse pass (#43382) · 347e4b2e
      Sławomir Siwek 提交于
      * consolidate conv act passes
      
      * generalize conv_activation
      
      * integrate conv+act tests
      
      * code style format
      
      * whitespaces
      
      * remove timeout from old tests
      
      * implement comments from review
      
      * restore ut
      
      * whitespace
      
      * code style
      
      * transpose
      
      * fixes after review
      
      * method for gettin act
      
      * Change Paddle_enforce error type
      
      * code format
      
      * add missing opcompats
      347e4b2e