1. 22 9月, 2022 2 次提交
  2. 21 9月, 2022 2 次提交
    • Z
      Enable PaddleInference to use CINN. (#45009) · 3aa6bd57
      Zhen Wang 提交于
      * use cinn in the paddle inference
      
      * fix some cmake errors
      
      * Avoid division by zero in the arange_kernel.
      
      * Avoid dynamic ops.
      
      * Remove some useless codes.
      
      * Use OpTransInfo to encapsulate some codes used in the build_cinn_pass.
      3aa6bd57
    • W
      residual_no_bias (#46129) · aa0e84e3
      wenbin 提交于
      * residual_no_bias
      
      * comments
      
      * more ut
      
      * fix input
      aa0e84e3
  3. 20 9月, 2022 1 次提交
  4. 19 9月, 2022 1 次提交
  5. 13 9月, 2022 1 次提交
  6. 09 9月, 2022 1 次提交
  7. 07 9月, 2022 1 次提交
    • 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
  8. 06 9月, 2022 1 次提交
  9. 05 9月, 2022 2 次提交
  10. 31 8月, 2022 1 次提交
  11. 30 8月, 2022 2 次提交
    • Z
      Remove extra attribute in OpMaker (#44310) · fe321f9a
      zyfncg 提交于
      * add runtime config in phi
      
      * add runtime attr for op desc and op
      
      * fix no proto error
      
      * adjust opdesc set_attr impl
      
      * try to remove conv_op extra attrs
      
      * add init runtime attr map
      
      * change extra header path
      
      * fix runtime_attr
      
      * fix trace_op
      
      * fix bug of pass
      
      * fix merge conflict
      
      * fix dygraph attrs
      
      * fix bug of pass
      
      * fix dygraph bug
      
      * fix unittest module
      
      * delete extra attr default
      
      * fix dropout kernel
      
      * polish code
      
      * fix extra output of instance_norm
      
      * fix merge confilct
      
      * fix op_desc bug
      
      * add extra attr in yaml for conv3d_transpose
      
      * don't remove extra input and output
      
      * fix save_inference_model
      
      * fix bug of batch_norm
      
      * revert some change
      
      * polish log
      
      * polish code
      
      * add code comment
      Co-authored-by: NChen Weihang <chenweihang@baidu.com>
      fe321f9a
    • Z
      [Paddle-TRT] constant-folding (#45494) · 97f43a8e
      zhoutianzi666 提交于
      add constant folding pass, for some model,it will get less latency;
      97f43a8e
  12. 29 8月, 2022 1 次提交
    • Z
      [new_exe] Dy2Static support new_executor (#44450) · aba1295b
      zhangbo9674 提交于
      * add interpretercore
      
      * refine backward program id
      
      * add code
      
      * refine program
      
      * refine code
      
      * create forward/backward_program by prog2graph2prog method
      
      * test, do not care
      
      * refine code
      
      * refine code
      
      * refine code
      
      * test, do not care
      
      * add interpretorcore
      
      * add scope
      
      * refine scope create method
      
      * add jit for new_exe
      
      * solve conflict
      
      * delete unused code
      
      * polish code
      
      * polish code
      
      * refine scope in inplace
      
      * refine for datatransfer
      
      * refine _rebuild_from_desc
      
      * refine control eager deletion attr
      
      * refine used_for_jit
      
      * refine jit for infer
      
      * op size0 use ori program
      
      * polish code
      
      * refine jit
      
      * refine run_program_op ut
      
      * refine inplace
      
      * refine control
      
      * refine graph helper
      
      * refine control
      
      * refine inplace
      
      * refine buffer_share_inplace_pass
      
      * polish code
      
      * polish code
      
      * refine usage for compilerProgram
      
      * refine control
      
      * test
      
      * test core cache
      
      * refine code
      
      * refine io.py
      
      * increase test_seq2seq timeout
      
      * refine convert program
      
      * refine interpretercore_cache release
      
      * delete buildinplace
      
      * refine partial_program && io
      
      * refine code for io
      
      * test
      
      * test
      
      * test
      aba1295b
  13. 24 8月, 2022 1 次提交
  14. 22 8月, 2022 3 次提交
  15. 17 8月, 2022 1 次提交
  16. 16 8月, 2022 2 次提交
    • F
      convert multihead to oss (#45019) · f706d95d
      feng_shuai 提交于
      * convert multihead to oss
      
      * fix:bug
      
      * fix:delete const cast
      
      * fix:don't support bias_qk
      
      * add vit pass
      
      * fix:convert bug and add preln_residual_bias
      
      * support length=-1
      
      * add UT for convert
      
      * add no_bias_qk support for gpu_multihead_op
      
      * delete infer_shape depends on bias_qk
      
      * oss just can be used in T4 and A*
      
      * fix:change api for ROCM CI
      f706d95d
    • W
      fix new quant (#45155) · 2fb65e44
      Wangzheee 提交于
      2fb65e44
  17. 15 8月, 2022 1 次提交
  18. 12 8月, 2022 1 次提交
    • S
      Offload calculations from matmul op to fuse pass (#44941) · acb78ea2
      Sławomir Siwek 提交于
      * remove v2_transpose_reshape
      
      * matmul_transpose_reshape
      
      * reshape_transpose_matmul
      
      * Add int8 support for matmulV2
      
      * restore ut
      
      * adjust old ut
      
      * restore parallel UT ruels
      
      * remove mkldnn code from base ops
      
      * move enforces to pass
      
      * remove duplicated functions
      
      * delete duplicated enforces
      
      * feedback from review
      
      * add comments to variables
      
      * enable eltwise support
      
      * dynamic attribute
      
      * remove fusepass tests from op test
      
      * remove fuse pass cases from op test
      
      * revert introduction of dynamic attributes
      
      * style
      Co-authored-by: Nwozna <joanna.wozna@intel.com>
      acb78ea2
  19. 11 8月, 2022 1 次提交
  20. 10 8月, 2022 1 次提交
  21. 09 8月, 2022 2 次提交
  22. 05 8月, 2022 2 次提交
  23. 04 8月, 2022 1 次提交
    • S
      Matmuls with activation and elementwise_add fuses (#44655) · 0420d514
      Sławomir Siwek 提交于
      * Add unit tests
      
      * matmul_v2 + activation
      
      * matmuls + elementwise_add
      
      * matmul_v2 postops
      
      * transform matmul to v2
      
      * opcompat
      
      * fix fusing matmul with multipe outs
      
      * add shape constraints
      
      * remove unused vars
      
      * change pass order
      
      * - Unit tests to be debugged
      
      - fix
      
      - refactor
      
      - diagnostic
      
      - more diagnostic
      
      - fix
      
      - Fix number two
      
      - fix
      
      - fix
      
      - fix
      
      - alpha added
      
      - more fixes
      
      - compilation fix
      
      - removed diagnostic code
      
      - cosmetic fixes
      
      * lint
      
      * add alpha constraint
      
      * merge matmul refactor
      
      * trigger CI
      
      * - fix
      
      * - another fix
      
      * code style
      
      * add support for matmul+elementwise_add+activation
      
      * code style
      
      * fix bfloat16 bugs
      
      * change append_binary to append_sum
      Co-authored-by: NJacek Czaja <jacek.czaja@intel.com>
      0420d514
  24. 03 8月, 2022 1 次提交
  25. 02 8月, 2022 1 次提交
  26. 01 8月, 2022 2 次提交
  27. 27 7月, 2022 1 次提交
  28. 26 7月, 2022 3 次提交