1. 29 9月, 2022 1 次提交
  2. 28 9月, 2022 3 次提交
  3. 27 9月, 2022 3 次提交
    • W
      [Eager, Performance optimization] support divide( / operator) to sink to Cpp layer (#46329) · f20b361c
      Weilong Wu 提交于
      * [Eager] math op sink to Cpp level
      
      * fix ci errors
      
      * draft version
      
      * support + and - operator under cpp directly
      
      * add static test
      
      * polish code
      
      * promote types or unify right type to left
      
      * recover static test case
      
      * polish code and fix some ci errors
      
      * support complex and polish code
      
      * fix conflicts
      
      * fix windows ci errors
      
      * fix windows-inference-ci errors
      
      * polish and fix tests
      
      * fix test case
      
      * polish code
      
      * [Eager, Performance optimization] support multiply( * operator) to sink to Cpp layer
      
      * rm useless glog
      
      * [Eager, Performance optimization] support divide( / and // operator) to sink to Cpp layer
      
      * polish code
      
      * polish code and fix code-format
      
      * polish code
      
      * fix CI
      
      * polish code
      
      * update test
      
      * support div operator under cpp
      
      * fix scalar as input
      
      * Polish div logic, fix ci test
      
      * fix errors
      f20b361c
    • W
      [Eager] refine gil use (#46452) · b106c424
      wanghuancoder 提交于
      * refine gil use
      b106c424
    • Z
      [Sparse] Support static graph (#46245) · a02eb143
      zhangkaihuo 提交于
      a02eb143
  4. 26 9月, 2022 4 次提交
    • C
      Fix libpaddle soname mismatch error (#46344) · cdcc0013
      Chen Weihang 提交于
      * fix libpaddle soname mismatch error
      
      * fix windows failed
      
      * polish linux and windows make impl
      
      * unify winddows lib name
      
      * fix windows error
      
      * revert copy dst change
      
      * revert naming change
      
      * revert windows change
      
      * fix gpups compile failed
      cdcc0013
    • W
      [Eager, Performance optimization] support multiply( * operator) to sink to Cpp layer (#46326) · 7fb20b46
      Weilong Wu 提交于
      * [Eager] math op sink to Cpp level
      
      * fix ci errors
      
      * draft version
      
      
      * support + and - operator under cpp directly
      
      * add static test
      
      * polish code
      
      * promote types or unify right type to left
      
      * recover static test case
      
      * polish code and fix some ci errors
      
      * support complex and polish code
      
      * fix conflicts
      
      * fix windows ci errors
      
      * fix windows-inference-ci errors
      
      * polish and fix tests
      
      * fix test case
      
      * polish code
      
      * [Eager, Performance optimization] support multiply( * operator) to sink to Cpp layer
      
      * rm useless glog
      
      * polish code
      
      * polish code and fix code-format
      
      * polish code
      
      * fix CI
      
      * polish code
      7fb20b46
    • W
      [Eager, Performance optimization] math op sink to Cpp level ( + and - operator... · 23c50648
      Weilong Wu 提交于
      [Eager, Performance optimization] math op sink to Cpp level ( + and - operator as an example ) (#45811)
      
      * [Eager] math op sink to Cpp level
      
      * fix ci errors
      
      * draft version
      
      * draft version
      
      * draft version
      
      * support + and - operator under cpp directly
      
      * add static test
      
      * polish code
      
      * promote types or unify right type to left
      
      * recover static test case
      
      * polish code and fix some ci errors
      
      * support complex and polish code
      
      * fix conflicts
      
      * fix windows ci errors
      
      * fix windows-inference-ci errors
      
      * polish and fix tests
      
      * fix test case
      
      * polish code
      
      * polish code
      
      * polish code and fix code-format
      
      * polish code
      
      * polish code
      
      * polish code
      
      * polish code
      23c50648
    • C
      Enable eager mode on xpu (#46227) · 87a25fbd
      Chen Weihang 提交于
      * enable eager mode on xpu, test=kunlun
      
      * add numpy support to xpu
      
      * fix tensor using error
      
      * fix  error, test=kunlun
      
      * fix failed tests, test=kunlun
      87a25fbd
  5. 22 9月, 2022 1 次提交
  6. 21 9月, 2022 3 次提交
  7. 20 9月, 2022 4 次提交
  8. 19 9月, 2022 2 次提交
  9. 18 9月, 2022 1 次提交
  10. 16 9月, 2022 2 次提交
  11. 15 9月, 2022 3 次提交
  12. 14 9月, 2022 2 次提交
  13. 09 9月, 2022 5 次提交
  14. 08 9月, 2022 1 次提交
  15. 06 9月, 2022 4 次提交
  16. 05 9月, 2022 1 次提交
    • Y
      New format quant model support for MKLDNN (#45416) · 4e4f4586
      yeliang2258 提交于
      * support onnx format quantized model
      
      * update code
      
      * add test
      
      * add test
      
      * fix
      
      * fix test
      
      * fix cmake
      
      * update code
      
      * change scale file path to calibration file path
      
      * update code
      
      * update code
      
      * fix build bug
      
      * fix build bugs
      
      * fix
      
      * fix
      4e4f4586