"git@developer.sourcefind.cn:modelzoo/qwen_lmdeploy.git" did not exist on "009075d8a2f4540519b95865a53b640a1b34bd5b"
  • zjing14's avatar
    Add xdlops v4r4r4 into online compilation (#48) · fbdf4332
    zjing14 authored
    
    
    * init for v4r4 xdlops olc
    
    * refactor wrap
    
    * init impl of v4r4 nchw xdlops olc
    
    * tuning
    
    * test perf
    
    * fixed v4r4 nhwc
    
    * tuned v4r4 nhwc
    
    * use gridwise_gemm_xdlops_v2r3
    
    * swap a/b
    
    * add pointer support into offline v2r3
    
    * debugging v4r4r4 transform for olc
    
    * change timer of olc
    
    * refactor v4r4 xdlops nchw olc
    
    * remove transform fun in v4r4 xdlops nhwc olc
    Co-authored-by: default avatarChao Liu <chao.liu2@amd.com>
    fbdf4332
common_header.hpp 982 Bytes