Commit History

Autor SHA1 Mensaxe Data
  Lin Manhui 5f62d1a877 [Feat] Support multi-device inference and OCR batch inference (#3923) hai 6 meses
  a31413510 8e822d163c support multy device set device id in inference (#3925) hai 6 meses
  Tingquan Gao 795e04563d bugfix (#3869) hai 7 meses
  Lin Manhui 69f4ebf469 [Fix] Fix bugs and polish docs (#3859) hai 7 meses
  Lin Manhui b22032a045 Fix trt-fp16 (#3856) hai 7 meses
  Tingquan Gao c5b8ee46a3 support to enable CINN to infer (#3835) hai 7 meses
  a31413510 d913ae47db modify npu whitelist hai 7 meses
  Lin Manhui 0afce8098f [Docs] Remove authentication instructions in docs (#3791) hai 7 meses
  hong 29b7be320b dcu xpu inference support pir (#3604) hai 7 meses
  Lin Manhui 944b6d6a49 Allow import paddle (#3788) hai 7 meses
  Lin Manhui 3685fd2843 [Fix] Let HPIP not automatically choose pptrt when it is not available (#3782) hai 7 meses
  Lin Manhui f4a679ff9f [Feat] Support lazy imports (#3764) hai 7 meses
  a31413510 12ec01f6b8 upload npu ultra_infer tutorials (#3763) hai 7 meses
  Lin Manhui bc54f1bb90 [Infra] Prune and sort imports (#3694) hai 7 meses
  Lin Manhui a65d269b21 [Feat] Support multi-backend inference (#2860) hai 7 meses
  zhink 80cb6da064 fix Paddle-TRT some model within FP16 hai 8 meses
  gaotingquan c5c819d47b support to disable trt half ops hai 8 meses
  gaotingquan 696089a110 call enable_use_gpu() first to use TensorRT engine hai 8 meses
  gaotingquan 976eeb533f when pir trt, it's need that enabling use gpu in convert_trt hai 8 meses
  EnflameGCU 0599a222ed [GCU] Update gcu config (#3605) hai 8 meses
  gaotingquan 19863acc7f bugfix hai 8 meses
  gaotingquan db1bbfe948 support to set more trt config by model hai 8 meses
  gaotingquan d3dc02cb7a support to set trt config by model hai 8 meses
  gaotingquan 774737c06b support paddle_fp32 and paddle_fp16 mode hai 8 meses
  zhang-prog eb3e60685b add cache func (#3509) hai 8 meses
  gaotingquan 5abc0bfdca set trt config for PP-YOLOE_seg-S hai 8 meses
  gaotingquan bf87804450 support trt_dynamic_shape_input_data for pir trt hai 8 meses
  gaotingquan 0742a15ef8 Manually delete the predictor to trigger its destructor, ensuring that the shape_range_info file would be saved hai 8 meses
  Lin Manhui bea5ad68f9 [Fix] Allow bypassing model white list checks when performing internal tests (#3499) hai 8 meses
  gaotingquan ded6b3ab2b bugfix: call enable_use_gpu() before calling enable_tensorrt_engine() hai 8 meses