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 2.2.05Oct432130Sep292827262524232221201918171514131211109764331Aug2928272524232221201918171615141311109865432131Jul302927262524232221201918171615141312111098765432130Jun2827262524232221201917151413121110876543131May3029Fix dmlc-core path in nnvm Makefile (#1829)[DOCKER] Fix CI script (#1826)Add SGX to docker (#1822)[RELAY][DOCS] Core Operator docs (#1821)[RUNTIME] Fix debug runtime i386 build (#1818)[DEBUG]Support a debug framework for TVM Runtime (#1378)[TVM] Fix negating undefined in DetectLinearEquation (#1816)Correction in documentation (#1810)[RELAY][OP] conv2d, ShapeExpr->IndexExpr (#1798)[Tutorial] tutorial for tensorize (#1774)[AUTOTVM] Support multiple targets load in tophub (#1803)Change cat image extension to png to match its download URL (#1800)Use ctx instead of tvm.gpu(0) in nnvm_quick_start tutorial (#1801)Fix vulkan build with homebrew install of vulkan-sdk (#1802)[TOPI] Update TopHub and benchmark (#1796)Change error.h path in doc.h (#1794)[NNVM][TEST] Numgrad: fix nan and multioutput (#1754)[TOPI] Add conv2d int8 template (#1735)[NODE] Keep base node system in HalideIR (#1793)[RELAY] First pass at pretty printer (#1749)[IR] eager constant folding in operator overloading (#1789)[Relay] Incorporate TypeRelations into more tests (#1792)Add atol=1e-5 to test_topi_matmul.test_matmul (#1791)Add docs/dev/relay_add_op.rst to docs/dev/index.rst (#1790)[Relay] Free Variables (#1786)[BUG] Fix incorrect libcuda.so found by cmake when multiple versions of CUDA exist (#1788)Implement tensorflow relational operators and related tests (#1714)support of multiple devices for tvm.build (#1773)[NNVM][TENSORFLOW]Fix lstm testcase to support get_output without size input (#1731)[Relay][DOC] Add tutorial for adding an operator to Relay (#1778)[RELAY] Refactor type inference to use type solver (#1779)Added Dockerfile demonstrating OpenCL & OpenGL installation (#1770)[SGX] Improve edgeroutines (#1775)Adding source types to C++ reduce functions (#1771)[ONNX][FRONTEND] Constantfill - #1539 (#1764)[TOPI] Access topi::matmul from Python (#1744)[Relay] Restore kind checking (#1758)[RUNTIME] Use weak link for fp16 functions (#1769)INT8 conv operator implementation with NCHWc data layout for Intel machines (#1680)[RUNTIME] Add fp16/fp32 conversion functions (#1766)