1. 26 5月, 2023 2 次提交
  2. 25 5月, 2023 4 次提交
  3. 24 5月, 2023 1 次提交
  4. 23 5月, 2023 3 次提交
  5. 22 5月, 2023 3 次提交
  6. 19 5月, 2023 1 次提交
  7. 18 5月, 2023 2 次提交
    • H
      Fused elementwises kernels and ops (#51427) · fb4a6ecf
      Hulek 提交于
      * Fused elementwises kernels and ops
      
      * change fuse pass name
      
      * adjust .pbtxt files
      
      * adjust quantization attributes
      
      * add missing arguments and fix others, review fixed
      
      * simplify fused kernel registration
      
      * fix elementwise unit tests
      
      * reuse one fused elementwise op
      
      * adjust proto
      
      * Add supported datatypes
      
      * Change 'Scale' to 'scale' in tests, change some tests to onednn
      
      * Revert breaking changes
      
      * Fix unit tests
      
      * Delete obsolete test cases
      
      * Delete commented out code
      
      * Fix codestyle
      
      * delete temporary condition
      
      * fix conflicts and delete duplicate fusing
      
      * Fix code after merge
      
      * Move tests to new directory
      
      * fix tests volatility
      
      * Rename test_elementwise_add_onednn_op.py to test_elementwise_add_mkldnn_op.py
      
      * Update CMakeLists.txt add mkldnn op test
      
      ---------
      Co-authored-by: NSilv3S <slawomir.siwek@intel.com>
      fb4a6ecf
    • H
      move fusion_group kernel to phi (#53781) · 26da689d
      huangjiyi 提交于
      26da689d
  8. 16 5月, 2023 4 次提交
  9. 11 5月, 2023 1 次提交
  10. 10 5月, 2023 1 次提交
  11. 09 5月, 2023 2 次提交
  12. 08 5月, 2023 2 次提交
  13. 05 5月, 2023 2 次提交
  14. 04 5月, 2023 1 次提交
  15. 27 4月, 2023 1 次提交
  16. 25 4月, 2023 2 次提交
  17. 24 4月, 2023 2 次提交
  18. 23 4月, 2023 1 次提交
  19. 21 4月, 2023 1 次提交
  20. 19 4月, 2023 1 次提交
  21. 17 4月, 2023 1 次提交
    • Z
      [Paddle-Inference] Add cutlass conv2d_depthwise (#51792) · bd3b096a
      zhoutianzi666 提交于
      * initial commit for cutlass_teller
      
      * second commit for cutlass_teller
      
      * add conv2d_depthwise python template
      
      * add conv2d_depthwise cutlass template
      
      * /zhoukangkang/paddle_cutlass/Paddle/paddle/fluid/framework/ir/cutlass_teller.h
      
      * refine code in Conv2dFusionCanSupport
      
      * add macro in cutlass_teller.h
      
      * add 3x3 5x5 teller
      
      * add groups not 1 or conv2d_depthwise teller
      
      * 只生成ic是8的倍数的conv2d_depthwise 的kernel
      
      * add EXPLICIT in cutlass_teller.h
      
      * final commit
      
      * add split_k_slices in conv2d_depthwise
      
      * make stages == 2
      
      * 重构部分代码
      
      * add CutlassFusionType
      
      * solve illegal memory
      
      * make stride_h=stride_w && make dilation==1
      
      * must check HasAttr(use_cutlass) before GetAttrIfExists
      
      * add CONV2D_DEPTHWISE_BIAS_SILU to OpType2String
      
      * modify decl.h and util.cu
      bd3b096a
  22. 14 4月, 2023 1 次提交
  23. 13 4月, 2023 1 次提交