Geçmişin Kaydedilmesi

Yazar SHA1 Mesaj Tarih
  gaotingquan 976eeb533f when pir trt, it's need that enabling use gpu in convert_trt 8 ay önce
  EnflameGCU 0599a222ed [GCU] Update gcu config (#3605) 8 ay önce
  gaotingquan 19863acc7f bugfix 8 ay önce
  gaotingquan db1bbfe948 support to set more trt config by model 8 ay önce
  gaotingquan d3dc02cb7a support to set trt config by model 8 ay önce
  gaotingquan 774737c06b support paddle_fp32 and paddle_fp16 mode 8 ay önce
  zhang-prog eb3e60685b add cache func (#3509) 8 ay önce
  gaotingquan 5abc0bfdca set trt config for PP-YOLOE_seg-S 8 ay önce
  gaotingquan bf87804450 support trt_dynamic_shape_input_data for pir trt 8 ay önce
  gaotingquan 0742a15ef8 Manually delete the predictor to trigger its destructor, ensuring that the shape_range_info file would be saved 8 ay önce
  Lin Manhui bea5ad68f9 [Fix] Allow bypassing model white list checks when performing internal tests (#3499) 8 ay önce
  gaotingquan ded6b3ab2b bugfix: call enable_use_gpu() before calling enable_tensorrt_engine() 8 ay önce
  Lin Manhui 8412aa82cb Circumvent paddle inference bug (#3490) 8 ay önce
  zhang-prog 3c9400e6dd Enhance benchmark (#3475) 8 ay önce
  zhang-prog 5158085f23 [Feat] upgrade benchmark (#3416) 8 ay önce
  gaotingquan 9a4a934d47 support set trt config by model 8 ay önce
  a31413510 7b5288bd6f predict 8 ay önce
  gaotingquan 68f3ff5b6f fix redundantly create predictor 9 ay önce
  gaotingquan f48f8e4fdf call enable_gpu() on dcu device 9 ay önce
  gaotingquan a5b997876d use dcu device type 9 ay önce
  gaotingquan fcbf6b11d2 dcu also use gpu as the flag 9 ay önce
  gaotingquan 8e9b8ddca2 change workspace_size to 30 in trt infer to be compatible with more models 10 ay önce
  gaotingquan adb12d98b6 update trt 10 ay önce
  gaotingquan e0fcc1ff5f support PIR TRT 10 ay önce
  gaotingquan f1ba03b2e9 update Paddle Predictor 10 ay önce
  Tingquan Gao 5fb83f71f3 deprecate NEW_PREDICTOR & USE_NEW_INFERENCE flags (#2932) 9 ay önce