578 Commits (1add4517ad21635490620d3b6b6416b8aa1dcce4)

Author SHA1 Message Date
  Megvii Engine Team 95ac055538 feat(dnn,mgb,imperative): add diag opr implement 3 years ago
  Megvii Engine Team 39d77fb55a feat(arm): add arm rnn_cell/lstm_cell/lstm optimized kernel 3 years ago
  Megvii Engine Team f509b1be9b fix(build): split elemwise_multi_type cpp 3 years ago
  Megvii Engine Team 3251f50114 fix(mgb/cuda-stub): add libcuda-wrap_11.4.h to fit the CUDA11.4 toolchain 3 years ago
  Megvii Engine Team ee0b95e935 feat(dnn/elemwise/arm_common): support part of arm ternary elemwise multithread 3 years ago
  Megvii Engine Team cbbca5fb10 feat(mge): add softmax op use cudnn api 3 years ago
  Megvii Engine Team 20b42a8c3b fix(dnn): add naive lstm kernel 3 years ago
  Megvii Engine Team 2faa6ea5a9 Merge pull request #213 from kxz18:rnn 3 years ago
  Megvii Engine Team 82be0aaced test(dnn): fix compute capability requirement for NCHWX test 3 years ago
  Megvii Engine Team 3b41840b68 fix(mgb): change caffepooling log level 3 years ago
  Megvii Engine Team 1999307015 feat(mgb/opr): add dropout kernel 3 years ago
  Megvii Engine Team 32717b0ca4 fix(build): split some cpp, which consume two many mem when build 3 years ago
  Megvii Engine Team a93741815b feat(mgb/opr): add layernorm forward and backward kernel 3 years ago
  Megvii Engine Team a404cd7d06 fix(mgb/src): add tensorRT version check 3 years ago
  Megvii Engine Team c53cad2049 feat(cmake): format all cmake file 3 years ago
  Megvii Engine Team a5803058b4 fix(dnn/x86): opt algo order 3 years ago
  Megvii Engine Team 93310c0e4b fix(mgb/gopt): fix cpu global layout transform fastrun error 3 years ago
  Megvii Engine Team c90e0b54be perf(arm): optimize arm uint16 relayout with n=4 3 years ago
  Megvii Engine Team f6d9909460 feat(dnn): add elemwise multi type support i16xf32 and u8xf32 3 years ago
  Megvii Engine Team d9a46ea47b fix(dnn): correct behaviour of floor div for int tensor 3 years ago
  Megvii Engine Team 0ad5eeaedd feat(mgb/gopt): global layout transform support opencl 3 years ago
  kxz@thumt102-1 8f48da7ffe feat(mgb/opr): add cell level rnn/lstm and sequence level rnn/lstm 3 years ago
  Megvii Engine Team 2881934cb8 feat(dnn/check_non_finite): addmul scale to check_non_finite opr 3 years ago
  Megvii Engine Team 6bb5409976 feat(dnn/src): add images2neibs kernel of opencl and related test 3 years ago
  Megvii Engine Team 6ce4a34403 feat(dnn): add fallback postprocess 3 years ago
  Megvii Engine Team c96dbd29b8 fix(dnn/arm_common): support more monotonous case in arm typecvt for performance 3 years ago
  Megvii Engine Team ead611e11d perf(dnn): slightly improve arm neon transcendental function performance 3 years ago
  Megvii Engine Team 0d16952470 fix(mgb/cuda): fix conv error when the input tensor is too large 3 years ago
  Megvii Engine Team 02d5f46d90 fix(mgb/x86): fix convbias crash on X86 3 years ago
  Megvii Engine Team accb2d8d47 fix(mgb/serialize): fix flatbuffer compatibility issues 3 years ago
  Megvii Engine Team 5e07e1e0f9 fix(dnn/falback): let cpu be able to execute int4 model 3 years ago
  Megvii Engine Team 2696e4efaa feat(dnn): add float16 for remap backward 3 years ago
  Megvii Engine Team 1f0cc891b0 feat(dnn): enable eye to support bool 3 years ago
  Megvii Engine Team 11d75fecb5 feat(dnn/check_non_finite): add batch check_non_finite 3 years ago
  Megvii Engine Team 2318ea3f15 fix(dnn): fix naive average pooling overflow bug for int8 type 3 years ago
  Megvii Engine Team 2d54ad185b feat(lite): add global layout transform interface for load and run 3 years ago
  Megvii Engine Team ba2f0c2e48 fix(dnn/cuda): fix cudnn_conv algo of conv_bias opr for fp16 add z cases 3 years ago
  Megvii Engine Team 30976c239f fix(mgb/gopt): fix global layout transform 3 years ago
  Megvii Engine Team ca7cec7a5d fix(mgb/gopt): minor fixes for global layout transform 3 years ago
  Megvii Engine Team fe93013a6e feat(mgb/gopt): global layout transform support nchw_nchwxx hybrid mode 3 years ago
  Megvii Engine Team 3d45d35241 feat(mgb/gopt): profiler support checking algo availability 3 years ago
  Megvii Engine Team b59e8ccf24 fix(mgb): fix cambricon bangc copybara 3 years ago
  Megvii Engine Team 3116e128c5 fix(ci/integration_test): fix benchmark torch version 3 years ago
  Megvii Engine Team c85631aa77 feat(dnn): use ref ptr interface for all backends 3 years ago
  Megvii Engine Team d90cb7763c feat(src/core): record support change ptr basic 3 years ago
  Megvii Engine Team 89186edc5d fix(dnn): correct reduce/argmxx/fakequant calculation with nan 3 years ago
  Megvii Engine Team 68cdabd288 feat(opr): indexing_multi_axis_vec support nd index 3 years ago
  Megvii Engine Team a1cba6cc27 fix(dnn): fix convbias crash on X86 3 years ago
  Megvii Engine Team 9b4cd92ba3 fix(mgb/dnn): fix cudnnConvBiasActivation crash on nchw32 int8 with oc > 256 3 years ago
  Megvii Engine Team 23c1fda7e6 perf(arm_common): optimize sigmoid 3 years ago