10 Commits (c42ce9370581debfad9ef0499deaa867b623cec0)

Author SHA1 Message Date
  Megvii Engine Team afe9c4b50d feat(dnn/cuda): add implicit bmm kernels for large kernel depthwise convolution backward filter opr 3 years ago
  Megvii Engine Team 369c2ccc5a style(all): reformat c++ code 3 years ago
  Megvii Engine Team d69b59035d feat(dnn): add an get_all_algorithms_safe interface 3 years ago
  Megvii Engine Team 0708bc780c fix(dnn/cuda): disallow implicit dtype conversion in cublaslt matmul algos 3 years ago
  Megvii Engine Team ff0e6be7b9 fix(dnn/cuda): fix cutlass tensorop kernels 3 years ago
  Megvii Engine Team 336761253d feat(dnn/cuda): add tensorcore matmul for fp16 data type 3 years ago
  Megvii Engine Team ff755451d2 refactor(mgb): move algo's name from info to desc and delete some algo's unnecessary param() method 4 years ago
  Megvii Engine Team 2de2222e46 feat(dnn/cuda): add cutlass batched gemv kernel for matmul operator 4 years ago
  Megvii Engine Team 973d2a0ac2 feat(dnn/cuda): add cutlass matmul using split k parallel 4 years ago
  Megvii Engine Team 03c921f7c4 feat(dnn/cuda): add cutlass matmul impls 4 years ago