• P
    Speedup worker (#51760) · 8ca86d72
    pangengzheng 提交于
    * support run haokanctr model in heterps-models
    
    * polish setup.py
    
    * polish JVM_LIB in evn_dict
    
    * align infer auc with DistPsArch pre-stable
    
    * async and multi thread data feed
    
    * rewrite dense tensor intialization
    
    * async infer shape and reuse memory
    8ca86d72
fused_seqpool_cvm_op.cc 10.9 KB