Skip to content
Snippets Groups Projects
Select Git revision
  • clockwork default
  • clockwork-v0.6
  • master
  • v0.6.0
  • v0.5
  • v0.4
  • v0.3
  • v0.2
  • v0.1rc
9 results
You can move around the graph by using the arrow keys.
Created with Raphaël 2.2.013Nov121110976542131Oct30292827262524232221201918171615141312111098765432130Sep292827262524232221201918171514131211109764331Aug2928272524232221201918171615141311109865432131Jul302927262524232221201918171615141312111098765432130Jun2827262524232221201917151413121110876543131May3029[RELAY][PASS] General OpFusion. (#2090)[RELAY] Fix type info after mutation in simplify inference (#2093)[FRONTEND][ONNX]add Pad, ReduceMax, ReduceMin, ReduceMean and ReduceSum OP (#2061)[TOPI] depthwise-conv2d in NCHW[x]c layout for x86 (#2045)[VTA] Improved RPC for VTA (#2043)[TOPI][CUDA] int8 group conv2d (#2075)Add NNPACK to CI (#2085)[TVM] [NNPACK] Modernize and improve NNPACK bindings (#2084)[RELAY] CompileEngine update, nn conv2d, fix dense, pool. (#2082)[TEAM] vinx13 -> Reviewer (#2083)[OPENCL] Make use of cpu device when gpu device doesn't exist. (#2076)Fix conv2d int8 schedule on CUDA (#2074)[Frontend][MXNet] argmax, argmin ops support (#2048)Fix a crash in android_deploy demo. (#2073)fix asan check heap-use-after-free (#2071)Allow to use negative index of array in python (#2069)[CODEGEN][LLVM] Cache packed func ptr, lift alloca (#2070) [FRONTEND][ONNX] fixed operator converter for Split in onnx frontend (#2038)Add a testcase of dilated conv2d int8 (#2065)print import_llvm ir in tensorize tutorial (#2064)[RELAY][BACKEND] CompileEngine refactor. (#2059)[RELAY][RUNTIME] Add compute and schedule attributes for all ops in relay/op/tensor.py (#2050)Rename relay::Environment to relay::Module (#2054)[NNVM][OP] Allow two input tensors with different type in reshape_like op (#2052)[FRONTEND][TENSORFLOW] Enhancements. (#1923)[TOPI] Fix adding dilation arguments (#2047)Refine CMakeLists.txt (#2049)[RELAY][RUNTIME] Refactor interpreter and graph_runtime into consistent interface. (#2042)[Cleanliness] [Easy] Make TVM leak-sanitizer and Wnon-virtual-dtor clean. (#2046)[NNVM/TOPI][OP] gather_nd (#2041)[TOPI] Add dilation argument to conv2d and depthwise_conv2d (#1970)[RELAY] MobileNet (#1997)[RELAY/PASS] Simplify inference. (#2033)Better gemm support for cublas and cpu (#1967)[AUTOTVM] Misc fix to document and style (#2035)[TEAM] Add Zhi Chen as a reviewer. (#2040)[RELAY][RUNTIME] Add Relay interpreter and compiler for TVM runtime system. (#1954)[RELAY][OP] Maketuple to be resolved when containing incompleteType (#2031)[TOPI][AUTOTVM] Improve style (#2034)Fix a bug in inject-virtual-thread (#2039)