11 Commits (057b5bb515d551fa64decdb7350422c19feba447)

Author SHA1 Message Date
  nihui a7e3c62a1b
save foldable constants in file for reducing memory usage (#4337) 3 years ago
  nihui 92da26be79
pnnx load gpu torchscript and reset device (#4330) 3 years ago
  nihui bcf06bd1c0
fold new_full and full_like (#4323) 3 years ago
  nihui cef95f64a4
pnnx math operation (#4251) 3 years ago
  nihui f597619e94
pnnx export weight inside moduleop (#3902) 4 years ago
  nihui 0aba8af1d3
pnnx swin transformer (#3783) 4 years ago
  nihui f9c4e90962
catch more foldable constant in static shape inference mode (#3738) 4 years ago
  nihui f9663d7726
pnnx support torch 1.11.0 (#3617) 4 years ago
  nihui 340b4e673e
pnnx fold constant (#3521) 4 years ago
  teng e24a2e6c40
[fix] fix typo (#3377) 4 years ago
  nihui e4c821a468
PNNX is an open standard for PyTorch model interoperability (#3262) 4 years ago