تاریخچه Commit ها

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