1. 14 4月, 2022 4 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
    • S
      bda4965a
    • B
      add mkldnn int8 pass [step3] (#41599) · 8e2d4d30
      baoachun 提交于
      * add mkldnn int8 pass [step3]
      
      * Add test for compute_propagate_scales_mkldnn_pass
      
      * update pass
      
      * update api comment and python api
      Co-authored-by: Nwozna <joanna.wozna@intel.com>
      8e2d4d30
    • J
      Added shuffle_channel BF16/FP32 FWD oneDNN kernel (#39756) · c7623d72
      jakpiase 提交于
      * added shuffle_channel bf16/fp32 fwd kernel
      
      * added missing files
      
      * CI fix
      
      * changed from pten to phi
      
      * tmp save
      
      * added reviewers suggestions
      
      * fix for test
      c7623d72
  2. 13 4月, 2022 1 次提交
    • F
      init roll convert (#41689) · 14c3c450
      feng_shuai 提交于
      * init roll convert
      
      * add ut for roll convert
      
      * roll convert don't support trt6.0
      
      * fix: change ut for trt 7.0.0.1
      14c3c450
  3. 12 4月, 2022 2 次提交
  4. 07 4月, 2022 3 次提交
  5. 06 4月, 2022 1 次提交
  6. 02 4月, 2022 1 次提交
  7. 31 3月, 2022 2 次提交
    • W
      add multiclass nms3 trt converter (#41181) · 08c3edb3
      wangxinxin08 提交于
      * add multiclass_nms3 converter
      08c3edb3
    • T
      Using DistConfig in Paddle Inference (#41128) · dc0702fe
      TeslaZhao 提交于
      * Pass compat of conv_transpose_bias_mkldnn_fuse_pass
      
      * Fix a bug of strided_slice op, about the axes parameter access memory out of bounds
      
      * Fix a bug of strided_slice op, about the axes parameter access memory out of bounds
      
      * Fix a bug of transpose op, about accessing memory out of bounds of the perm param
      
      * op:transpose_op supports bool type
      
      * op:transpose_op supports bool type
      
      * Keep strided_slice op behavior consistent with slice op when starts input is less than -rank
      
      * Using DistConfig in inference
      dc0702fe
  8. 30 3月, 2022 1 次提交
  9. 18 3月, 2022 1 次提交
  10. 17 3月, 2022 3 次提交
    • H
      CopyFromCpu and CopyToCpu of Onnxruntime back-end optimize (#40561) · fcbb7440
      heliqi 提交于
      * add onnxruntime predictor
      
      * Add code comments
      
      * support link paddle2onnx onnxruntime
      
      * support onnxruntime with python
      
      * support onnxruntime with python
      
      * support onnxruntime with windows
      
      * paddle2onnx compile with windows
      
      * supoort windows compile
      
      * supoort windows compile with onnxruntime
      
      * supoort windows compile with paddle2onnx
      
      * supoort mac compile
      
      * compile with mac
      
      * compile with mac
      
      * add code comments
      
      * fix remind word
      
      * code optimization
      
      * add test case
      
      * add test case
      
      * add inference demo_ci test case
      
      * fix compile paddle2onnx with no python
      
      * add inference demo_ci test case
      
      * add inference demo_ci test case
      
      * add inference infer_ut test case
      
      * support c go api and test cases
      
      * add converage test case
      
      * add converage test case
      
      * add capi test case
      
      * add capi test case
      
      * fix onnxruntime copyfromcpu and copytocpu
      
      * fix goapi
      
      * modify code
      fcbb7440
    • Y
      [fleet executor] fleet executor for npu (#40607) · 81848fff
      Yuang Liu 提交于
      81848fff
    • B
      support gpu mixed precision inference (#40531) · 06fee998
      baoachun 提交于
      06fee998
  11. 14 3月, 2022 1 次提交
    • T
      Add an elementwise + activation fusion pass. (#36541) · 3f219160
      Tomasz Socha 提交于
      * Add elementwise add and activation fuse pass
      
      * Fix copy ellision
      
      * More flexible pattern detector
      
      * More flexible fusion pass
      
      * Update lists for pass
      
      * Add support for Pow operator
      
      * Add support for more activation types
      
      * Style
      
      * Rename fusion pass
      
      * First version of tests
      
      * Dirty version of pass
      
      * Polished version
      
      * Update pbtxt
      
      * Style
      
      * Update names
      
      * Style
      
      * Use PADDLE_ENFORCE_EQ
      
      * Save error message to variable
      
      * WO for error checks
      
      * CR
      
      * Static style check
      
      * Add missing 'activation_scale' attribute
      
      * Add relu6 and sigmoid activations
      
      * Style
      
      * Fix fuse list formating
      
      * Sync filenames for fuse pass files
      
      * Fix cmake after move
      
      * Fix registration
      
      * Fix pass name in tests
      
      * Add missing activations to checker
      
      * WIPS
      
      * Working mul op
      
      * Working sub
      
      * Working Add
      
      * Remove pten includes
      
      * Remove some forward declarations
      
      * Remove Includes
      
      * Fixes
      
      * Remove default kernels
      
      * Add check if post_ops attributes are avaliable
      
      * Style
      
      * Code adjustment
      
      * Register default kernels
      
      * We have year 2022 not 2021...
      Co-authored-by: Njakpiase <jakpia21@gmail.com>
      Co-authored-by: NSylwester Fraczek <sylwester.fraczek@intel.com>
      
      * Fast review fixes
      Co-authored-by: Njakpiase <jakpia21@gmail.com>
      Co-authored-by: NSylwester Fraczek <sylwester.fraczek@intel.com>
      
      * Review Fix
      
      * Rename one_dnn -> onednn
      
      * Style after review
      
      * Fast and dirty fix for quantization
      
      * Update tests
      
      * Style
      
      * Fix mkldnn_quantizer config
      
      * Add Joanna's suggestion.
      
      * Check if operator is explicitly disables on OneDNN
      
      * Try to use unregistered attributes
      
      * Style
      
      * Test new framework
      
      * FXI
      
      * FXII
      
      * Update test
      
      * Style
      Co-authored-by: Njakpiase <jakpia21@gmail.com>
      Co-authored-by: NSylwester Fraczek <sylwester.fraczek@intel.com>
      3f219160
  12. 10 3月, 2022 1 次提交
    • H
      Inference add ONNXRuntime back-end (#39988) · 431afc39
      heliqi 提交于
      * add onnxruntime predictor
      
      * Add code comments
      
      * support link paddle2onnx onnxruntime
      
      * support onnxruntime with python
      
      * support onnxruntime with python
      
      * support onnxruntime with windows
      
      * paddle2onnx compile with windows
      
      * supoort windows compile
      
      * supoort windows compile with onnxruntime
      
      * supoort windows compile with paddle2onnx
      
      * supoort mac compile
      
      * compile with mac
      
      * compile with mac
      
      * add code comments
      
      * fix remind word
      
      * code optimization
      
      * add test case
      
      * add test case
      
      * add inference demo_ci test case
      
      * fix compile paddle2onnx with no python
      
      * add inference demo_ci test case
      
      * add inference demo_ci test case
      
      * add inference infer_ut test case
      
      * support c go api and test cases
      
      * add converage test case
      
      * add converage test case
      
      * add capi test case
      
      * add capi test case
      431afc39
  13. 08 3月, 2022 1 次提交
  14. 03 3月, 2022 2 次提交
  15. 02 3月, 2022 2 次提交
  16. 01 3月, 2022 1 次提交
  17. 25 2月, 2022 1 次提交
  18. 23 2月, 2022 1 次提交
  19. 22 2月, 2022 1 次提交
  20. 20 2月, 2022 1 次提交
  21. 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
  22. 17 2月, 2022 1 次提交
    • S
      [bugfix] to concat input squash (#39593) · f29da150
      Sylwester Fraczek 提交于
      * fix and add more tests
      
      * remove unwanted changes
      
      * check only concat and elementwise
      
      * move check to a function
      
      * add todo comment
      
      * Revert "fix ptq fc attr name fuse_activation->activation_type"
      
      This reverts commit ffd023353a5e9b0fd15e81b9e9f9fe1794035017.
      f29da150
  23. 16 2月, 2022 1 次提交
  24. 15 2月, 2022 2 次提交
    • W
      [Paddle-Inference] support preln_ernie: add... · 2bc91cc5
      Wangzheee 提交于
      [Paddle-Inference] support preln_ernie: add preln_embedding_eltwise_layernorm_fuse_pass, preln_skip_layernorm_fuse_pass (#39508)
      
      * support preln_ernie
      
      * support preln_ernie
      2bc91cc5
    • 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
  25. 14 2月, 2022 1 次提交
    • S
      [Bug fix] prevent squashing pair u8 dequantize -> s8 quantize (#39346) · 66b5348e
      Sylwester Fraczek 提交于
      * prevent squashing pair u8 dequantize -> s8 quantize
      
      * add relu op to check for uint8
      
      * fix ptq fc attr name fuse_activation->activation_type
      
      * fix
      
      * add unit test
      
      * remove unused variable
      
      * test fix unsuccessful
      
      * fix test and logic
      
      * multiline comment
      
      * remove cout
      
      * Revert "fix ptq fc attr name fuse_activation->activation_type"
      
      This reverts commit ffd023353a5e9b0fd15e81b9e9f9fe1794035017.
      
      * fix ptq fc attr name fuse_activation->activation_type
      66b5348e
  26. 11 2月, 2022 1 次提交
  27. 10 2月, 2022 1 次提交
  28. 09 2月, 2022 1 次提交