Skip to content
Snippets Groups Projects
Select Git revision
  • summer default
1 result
You can move around the graph by using the arrow keys.
Created with Raphaël 2.2.023Jun22211918171615141312111098765432131May30292827262524232221201918171615141312111098765130Apr2928272625242322212019171615141312119876532131Mar302928262524232221201918171615141312add tile module (#5234)Dev argsort eager (#5273)Release lambda function to reuse tensor memory (#5266)shorten XXIsDynamic4ArgNameAndIndex to be xxIsDynamic (#5265)Support XLA with CPU-only (#5260)job_config to cfg (#5235)delete onnx (#5258)[Functional] Part4: Migrate array ops (#5247)[Functional] Part3: Migrate binary and activation ops (#5246)rm onnx from ci (#5257)Fix GRPC compilation failure on CMake 3.20 (#5255)Refine header file copy (#5254)Reconstruct module files (#5251)Fix conv module bug (#5245)Refactor Memory Zone (#5072)Fix older version CMake doesn't support multiple targets in CLI (#5248)Fix bce withlogitloss ci error (#5237)Add test for convtranspose2d (#5239)[Functional] Part2: Add partial unary and math functional apis (#5218)Turn off NCCL_STATIC/CUDNN_STATIC when OF_CUDA_LINK_DYNAMIC_LIBRARY is ON (#5243)Add interface InferContext::OutputTensorDesc (#5219)Fix support for Ninja and add Ninja build in Simple CI (#5236)Add cmake option CUDA_STATIC (#5164)Add GroupNorm (#5175)[Add] avgpool1d avgpool3d (#5165)Fix protobuf debug postfix (#5233)Move default third party dir into build dir (#5230)Refine deconv kernel (#5229)Refine module test (#5232)add ReflectionPad2d (#5172)Op expr infer tensor meta (#5064)module BCELoss (#5144)Dev norm op (#5178)Lazy construct functor to make sure that the operators has already been registered. (#5225)Add deconv cpu impl (#5224)Refine protobuf cmake (#5216)Add Simple CI, runs CPU-only on GitHub hosted servers (#5207)crossentropyloss and nllloss support ignore_index (#5195)Yejiaojiao/dev bcewithlogitsloss (#5173)Dev user op set default is_dynamic (#5223)