1. 15 11月, 2022 2 次提交
    • J
      Added optimization pass for oneDNN layernorm kernel (#47782) · 519e7426
      jakpiase 提交于
      * optimization for ln
      
      * fix
      
      * added output to gpd
      
      * added formatting
      
      * fix
      519e7426
    • S
      mkldnn directory cleanup (#47779) · 8a339d24
      Sławomir Siwek 提交于
      * cleanup unused code
      
      * unify is_int8 is_bfloat16
      
      * Simplify matmul_v2 FWD kernel
      
      * remove RunKernel methods
      
      * remove import namespace
      
      * remove headers
      
      * clean fluid/phi cross imports
      
      * remove fluid axpy_handler
      
      * delete fluid methods
      
      * activations
      
      * OneDNNMemDesc
      
      * MKLDNNFormatForSize
      
      * MatchShapeToLayout
      
      * MKLDNNMemoryFormat
      
      * MKLDNNFormat
      
      * ReorderMKLDNNHandler
      
      * to_void_cast
      
      * review suggestions
      
      * interpolate
      
      * remove fluid depedency
      8a339d24
  2. 14 11月, 2022 1 次提交
  3. 11 11月, 2022 2 次提交
  4. 10 11月, 2022 3 次提交
  5. 08 11月, 2022 3 次提交
  6. 07 11月, 2022 2 次提交
  7. 04 11月, 2022 1 次提交
  8. 03 11月, 2022 3 次提交
    • Y
      Fix ComputePropagateScalesMkldnnPass of MKLDNN (#47574) · 5fc92943
      yeliang2258 提交于
      * add constant_folding_pass pass for mkldnn int8
      
      * update UpdateScaleOpInOutScales
      5fc92943
    • S
      [PHI] Migrate softmax kernel (#47339) · b8ae3858
      Sławomir Siwek 提交于
      * add extra attr property set
      
      * add type_info for all context
      
      * add onednn context to all context
      
      * fix context compile error
      
      * simplify conv kernel args
      
      * pass runtime attr into dev_ctx
      
      * fix marco error
      
      * clear conv_grad_kernel extra args
      
      * merge conv_grad_grad into conv_grad
      
      * clear conv2d_grad_grad extra attrs
      
      * remove redundant imports
      
      * migrate softmax
      
      * clear yaml and eager extra attr
      
      * fix conv1d error
      
      * change to thread local
      
      * fix npu compile failed
      
      * try to fix windows compile failed
      
      * add conv2d onednn phi kernel
      
      * fix ci bugs (#36)
      
      * fix compile bugs (#38)
      
      * fix extra input transform bug (#39)
      
      * support dynamic created attr (#40)
      
      * reset extra info gen code
      
      * rm conv_grad_grad kernel
      
      * reimpl pass attr adapting
      
      * add int attr support
      
      * remove vector inputnames creating
      
      * merge dev
      
      * fix map at error
      
      * adjust attribute
      
      * adapt funcs to PHI
      Co-authored-by: NChen Weihang <chenweihang@baidu.com>
      Co-authored-by: NYuanRisheng <yuanrisheng@baidu.com>
      b8ae3858
    • W
      bug fix (#47611) · 5160628c
      wenbin 提交于
      5160628c
  9. 02 11月, 2022 1 次提交
  10. 01 11月, 2022 1 次提交
  11. 31 10月, 2022 1 次提交
  12. 27 10月, 2022 2 次提交
  13. 26 10月, 2022 3 次提交
  14. 24 10月, 2022 1 次提交
  15. 21 10月, 2022 1 次提交
  16. 20 10月, 2022 2 次提交
  17. 19 10月, 2022 2 次提交
  18. 18 10月, 2022 2 次提交
    • W
      Merge layernorm trt fuse (#46320) · 5e9f491e
      Wang Bojun 提交于
      * first version, accuracy corrected
      
      * disable debug print
      
      * use blockReduceSum in phi
      
      * add UT
      
      * add opCompat
      
      * code style
      
      * code refine
      
      * bug fix
      
      * code refine
      
      * test fix
      
      * bugfix
      
      * codesytle fix
      
      * code style
      
      * code-style
      
      * code-style
      
      * code-style
      5e9f491e
    • S
      FC + activation fuse passes (#45183) · b7a23adb
      Sławomir Siwek 提交于
      * git
      
      * style
      
      * leave default relu in kernel
      
      * style
      
      * cleanup FCMKLDNN pattern
      
      * merge conflicts
      
      * update develop
      
      * update develop
      
      * add const
      
      * rename to oneDNN and adjust attributes
      
      * whitespace
      b7a23adb
  19. 17 10月, 2022 4 次提交
  20. 16 10月, 2022 1 次提交
  21. 13 10月, 2022 2 次提交
    • Y
      Fix quantize model deploy bugs when using MKLDNN (#45920) · 561fd8c8
      yeliang2258 提交于
      * fix immutable op quantize bugs
      
      * fix
      
      * fix build bug
      
      * fix test
      
      * notest,test=inference
      
      * fix ppyoloe acc drop bugs
      
      * fix test
      
      * fix test
      
      * add test
      
      * fix
      
      * fix
      
      * fix test
      
      * fix refined name bug
      
      * fix test
      
      * bias fix
      
      * fix matmul weight dequant bug
      
      * re-ci
      
      * fix tester
      
      * fix test
      
      * fix tester
      
      * update weight dequantize func
      
      * update code
      
      * update test for converage
      
      * update test
      
      * update cmake
      
      * update cmakelist
      
      * update code
      
      * rerun ci
      
      * remove useless code
      561fd8c8
    • J
      Add unsigned int8 scale propagation (#46378) · c72b3bfa
      joanna.wozna.intel 提交于
      * Add unsigned int8 propagation
      
      * Add or modify unit tests
      
      * Correct concat scale checking
      
      * Apply review suggestions
      
      * Corrections
      c72b3bfa