MegEngine

Commit Graph

Author	SHA1	Message	Date
Megvii Engine Team	f2b42bf09e	chore(dotprod): add arm dotprod attribute for easy use GitOrigin-RevId: `78c3e72218`	4 years ago
Megvii Engine Team	c33a717314	feat(dnn): repalce is_reproducible with algo attribute in opencl, cpu, rocm and cuda GitOrigin-RevId: `86dead0a11`	4 years ago
Megvii Engine Team	2de2222e46	feat(dnn/cuda): add cutlass batched gemv kernel for matmul operator GitOrigin-RevId: `51702c4e79`	4 years ago
Megvii Engine Team	973d2a0ac2	feat(dnn/cuda): add cutlass matmul using split k parallel GitOrigin-RevId: `650209e35f`	4 years ago
Megvii Engine Team	03c921f7c4	feat(dnn/cuda): add cutlass matmul impls GitOrigin-RevId: `619c8c299c`	4 years ago
Megvii Engine Team	5b62acfa01	feat(dnn/armv7): add new matmul strategy k8x8x4 GitOrigin-RevId: `0c6b7fa1b2`	4 years ago
Megvii Engine Team	9cc732f82d	fix(opencl): fix opencl search algo negative stride support GitOrigin-RevId: `0642d1718d`	4 years ago
Megvii Engine Team	c69359d00d	fix(dnn/cuda): disable cudnn conv_bias kernels for NCHW4_NCHW tensor format due to illegal memory access errors caused by the kernels GitOrigin-RevId: `584cedeeab`	4 years ago
Megvii Engine Team	2e4b9a42f7	fix(mgb/gopt): fix folding conv dimshuffle opt pass GitOrigin-RevId: `878b7de9de`	4 years ago
Megvii Engine Team	0e3a6329ff	build(cuda): support cu111 build GitOrigin-RevId: `b3067ba4d5`	4 years ago
Megvii Engine Team	e9db061e45	fix(mgb): fix compiling error for cuda-11.1 GitOrigin-RevId: `f63e71afa7`	4 years ago
Megvii Engine Team	cd7090acbb	fix(opencl): enable image on mali(cl2.1) GitOrigin-RevId: `0c670fba80`	4 years ago
Megvii Engine Team	c51a687cef	chore(mge): update copyright years GitOrigin-RevId: `46104ac891`	4 years ago
Megvii Engine Team	af42ce7e69	fix(megdnn): some fixes of execution policy GitOrigin-RevId: `920f39bcb6`	4 years ago
Megvii Engine Team	7afa422df4	refactor(megdnn): refactor sub opr setter GitOrigin-RevId: `475afb9c10`	4 years ago
Megvii Engine Team	821656aa4b	refactor(megdnn): refactor brute force algo in batched matmul GitOrigin-RevId: `5c143ab3ac`	4 years ago
Megvii Engine Team	08ff62deb6	refactor(megdnn): refactor batched matmul algo in conv bias GitOrigin-RevId: `64fda611ff`	4 years ago
Megvii Engine Team	8773926ef8	refactor(megdnn): refactor matmul algo in conv bias GitOrigin-RevId: `932f7d6f81`	4 years ago
Megvii Engine Team	e4b71bdf64	refactor(megdnn): remove unnessary 1x1 algo GitOrigin-RevId: `809f9b2bba`	4 years ago
Megvii Engine Team	44c8d2d16f	refactor(megdnn): refactor matmul algo in deformable conv GitOrigin-RevId: `05291baf98`	4 years ago
Megvii Engine Team	b04ad06f84	refactor(megdnn): refactor matmul algo in conv backward filter GitOrigin-RevId: `bb65777583`	4 years ago
Megvii Engine Team	25089e520e	refactor(megdnn): refactor matmul algo in conv backward data GitOrigin-RevId: `8de601df6e`	4 years ago
Megvii Engine Team	0d720653ac	refactor(megdnn): add default algo for convolution forward GitOrigin-RevId: `a12a7d399a`	4 years ago
Megvii Engine Team	659217acd2	refactor(megdnn): refactor bfloat16 convbias to recursive inteface GitOrigin-RevId: `378194fb7f`	4 years ago
Megvii Engine Team	4a1d52c9c6	refactor(megdnn): refactor bfloat16 matmul to recursive inteface GitOrigin-RevId: `641c508aec`	4 years ago
Megvii Engine Team	b8febaf91f	refactor(megdnn): refactor bfloat16 convolutionbackwardfilter to recursive inteface GitOrigin-RevId: `37c08a5b8b`	4 years ago
Megvii Engine Team	f14e0c17e7	feat(mgb): add recursive for fastrun and megdnn test GitOrigin-RevId: `743846f645`	4 years ago
Megvii Engine Team	85fa988348	refactor(dnn): add get_algorithm_from_desc interface GitOrigin-RevId: `6d211ca167`	4 years ago
Megvii Engine Team	2b8150ab52	fix(dnn): fix bazel build issue for cambricon platform GitOrigin-RevId: `a79e1b6f6a`	4 years ago
Megvii Engine Team	329306b031	fix(cmake/cuda): fix build at cuda `copy` env caused by b278a69e1 `copy` env vs `normal` env: case a:`normal` env install CUDNN/TRT by package tool, eg, apt/yum, which will put include file(cudnn.h/NvInfer.h) to /usr/include etc. case b: self copy env after export CPATH with cudnn/trt include dir case c: just copy libs, not export CPATH, only export TRT_ROOT_DIR/CUDNN_ROOT_DIR at case a and case b, BUILD system can find cudnn/trt headers, but at case c, can not find. `FIX` it! what`s more, recommend install CUDA env by case a and case c, NOT recommend install by case b, which caused by CUDA SDK CPATH not friendly to split c env, for example Android AOSP build env GitOrigin-RevId: `cb92123f9e`	4 years ago
Megvii Engine Team	364afec033	chore(mge): update copyright years GitOrigin-RevId: `3c0690bcc1`	4 years ago
Megvii Engine Team	ae8b38f634	fix(cmake/whl): reduce wheel size as some reason: some version of trt/cudnn need -Wl,--whole-archive attribute to fix cuda issue, target A(CMAKE OBJECT,eg megbrain/megdnn): -Wl,--whole-archive depend on trt/cudnn target B(SHARED LIBS,eg libmegengine.so) --> A with `PUBLIC` depends target C(SHARED LIBS,eg _impertive.so) --> B with `PUBLIC` depends, then ld will force link fatbin section into C, which will be undesired what`s more, attribute PUBLIC/PRIVATE do not take effect to OBJECT library(megbrain/megdnn) what`s more, megengine/megengine_export have to PUBLIC for mgb/imperative target, as SRC/include depends so we pull cudalib depend from megbrain/megdnn to megengine/megengine_export on linux os, to finall target at windows os, for example lar on windows GitOrigin-RevId: `b278a69e1c`	4 years ago
Megvii Engine Team	3bda334798	fix(dnn/fallback): fix segmentfault caused by im2col/conv1x1 using fallback naive matmul. GitOrigin-RevId: `03ef904b11`	4 years ago
Megvii Engine Team	87ff58f7fc	fix(megdnn): add algo for matmul/batchedmatrixmul of naive and opencl GitOrigin-RevId: `2409b6ba16`	4 years ago
Megvii Engine Team	a3caa5d3b7	fix(mgb(dnn)): fix convbias cudnnConvBiasActivation GitOrigin-RevId: `c0e44feffb`	4 years ago
Megvii Engine Team	55042195d4	chore(winograd): add Convolutionv2 param GitOrigin-RevId: `1a9e2ea340`	4 years ago
Megvii Engine Team	409a877267	feat(dnn): add algo interface for rocm&fallback matmul and batched matrix mul GitOrigin-RevId: `dea03a0f7a`	4 years ago
Megvii Engine Team	8f7f52ae4d	feat(jit): add memfwd in jit executor opr GitOrigin-RevId: `b58860bbe8`	4 years ago
Megvii Engine Team	dfb2b2ce49	fix(dnn): change pooling window size smaller than padding constraint to log_error GitOrigin-RevId: `c3cda68f6d`	4 years ago
Megvii Engine Team	a85531dd0f	feat(mgb/opr): add tqt opr GitOrigin-RevId: `49c62cd532`	4 years ago
Megvii Engine Team	c3a4b2225d	feat(dnn/cuda): add cutlass impls for fused convolution reformat operation GitOrigin-RevId: `02ef559c3f`	4 years ago
Megvii Engine Team	5f44203d7b	feat(dnn/cuda): add a cutlass impl for fusing convolution and dimshuffle GitOrigin-RevId: `3fc6faef01`	4 years ago
Megvii Engine Team	61f917fb8e	feat(dnn/cuda): add impl for fusing warp perspective and dimshuffle GitOrigin-RevId: `51e025973f`	4 years ago
Megvii Engine Team	eb826422c4	fix(dnn): forbid pooling window size smaller than padding GitOrigin-RevId: `9ad61c409d`	4 years ago
Megvii Engine Team	fc0fcd2f7f	chore(winograd): remove winograd transform code GitOrigin-RevId: `78c3cfceae`	4 years ago
Megvii Engine Team	d1adc9a22f	fix(dnn): fix opencl algo search GitOrigin-RevId: `25997d0ef1`	4 years ago
Megvii Engine Team	0398a7867f	fix(build/windows/cuda/llvm): fix windows bazel build with cuda * Adapt to the new version llvm/clang-11 * fix windows bazel build with cuda * add windows bazel build cuda ci * opt windows bazel ci scripts GitOrigin-RevId: `6ea7c66585`	4 years ago
Megvii Engine Team	3bf73ff16f	feat(dnn): add cuda preprocess fusion GitOrigin-RevId: `d789c99e59`	4 years ago
Megvii Engine Team	86cf7490ec	feat(dnn/aarch64): add quantizeds4 matmul int4x4x16_k8x8x8 GitOrigin-RevId: `7812900244`	4 years ago
Megvii Engine Team	142f31a875	perf(dnn/cuda): change conv_bias heu, prefer dnn chanwise impl, dislike dnn batch gemm conv1x1 GitOrigin-RevId: `323bf6073a`	4 years ago

... 3 4 5 6 7 ...

473 Commits (a6230ba95add1c8fac92f94654823dac238cd2bc)