1. 27 9月, 2022 2 次提交
  2. 26 9月, 2022 1 次提交
  3. 22 9月, 2022 2 次提交
  4. 21 9月, 2022 4 次提交
  5. 20 9月, 2022 6 次提交
  6. 19 9月, 2022 2 次提交
    • Z
      Fix wrong eigen header include (#46082) · 59a2a987
      zyfncg 提交于
      * fix wrong eigen header include
      
      * fix complie bug
      
      * fix nan_inf_utils_detail
      
      * fix resource_manager
      
      * fix conv_miopen_helper
      59a2a987
    • Y
      [PHI]Move sum op to PHI (#45860) · 4b3f2af1
      YuanRisheng 提交于
      * move sum
      
      * fix ci bugs
      
      * fix ci bugs
      
      * fix set_lod bugs
      
      * fix infershape bugs
      
      * fix ci bugs
      
      * fix ci unittest bug
      
      * fix ci bugs
      
      * perfect code
      
      * update code according comment
      
      * add unittest
      
      * fix ci bugs
      4b3f2af1
  7. 18 9月, 2022 1 次提交
  8. 17 9月, 2022 1 次提交
  9. 16 9月, 2022 1 次提交
  10. 15 9月, 2022 2 次提交
  11. 14 9月, 2022 5 次提交
  12. 09 9月, 2022 1 次提交
  13. 08 9月, 2022 5 次提交
  14. 07 9月, 2022 2 次提交
    • W
      Optimiza params sync between CPU and GPU. (#45805) · a2b2af90
      Wilber 提交于
      * enable memory optimize when fp16.
      
      * optimiza params sync between cpu and gpu.
      a2b2af90
    • 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
  15. 06 9月, 2022 3 次提交
  16. 05 9月, 2022 2 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
    • D
      Update DlNNE engine (#45027) · 638965c5
      denglin-github 提交于
      * add config param for enable_dlnne and support calibration mode
      * remove useless file
      * refine code and add annotation
      * refine code of Warnning tips
      638965c5