1. 21 Sep, 2023 3 commits
  2. 20 Sep, 2023 3 commits
  3. 19 Sep, 2023 1 commit
  4. 17 Sep, 2023 1 commit
  5. 16 Sep, 2023 5 commits
  6. 15 Sep, 2023 3 commits
  7. 14 Sep, 2023 3 commits
    • Umang Yadav's avatar
      Print warning about miopen_fusion while generating mxr (#2082) · 752f13cf
      Umang Yadav authored
      MIOpen fusions are not serialized with tuned solutions. Print warnings for such cases.
      752f13cf
    • Paul Fultz II's avatar
    • Brian Pickrell's avatar
      added rand_uniform operation closes #1958 (#2051) · fbd12bd3
      Brian Pickrell authored
      New op that populates a shape with random numbers with a uniform distribution. The rand_uniform op. can implement the Onnx RandomUniform instruction, and can also create the random number sequence necessary to implement Multinomial. (At this time, our Onnx Multinomial parsing generates a random sequence of numbers when parsing as a workaround, so that the resulting program uses the same "random" set every time.)
      
      Arguments: shape, seed. Shape is required; can be static or dynamic. Seed is still optional in this version. If it's not given at inference time, use the value in the creation attribute seed. Update: deleted A boolean use_auto_seed causes any given seed to be ignored.
      fbd12bd3
  8. 13 Sep, 2023 4 commits
  9. 12 Sep, 2023 1 commit
  10. 11 Sep, 2023 4 commits
  11. 10 Sep, 2023 3 commits
    • tvukovic-amd's avatar
      Fixed test float equal for Windows (#2153) · 37787e0b
      tvukovic-amd authored
      Added case to skip test_limits<int,long> while running tests on Windows since int and long have same min and max values
      37787e0b
    • Charlie Lin's avatar
      Dynamic allocate (#2079) · ede8bfa6
      Charlie Lin authored
      Makes a version of allocate that takes in dimensions and allocates a buffer
      Going to create a simplify_dynamic_ops compiler pass that will use the use_shape_attr flag
      The ONNX op ConstantOfShape needs the buffer to be filled with a specific value, so going to make another PR for that and a fill operator
      ede8bfa6
    • Lakhinder Walia's avatar
      Move operation for memory performance + misc changes for cpu performance (#2130) · b00489b3
      Lakhinder Walia authored
      Reduce memory footprint by std::move of temporary (potentially very large) containers.
      Minor cleanup for performance optimization: e.g. of Index() calculation -- which can get repeated millions of times in large tensors/vectors in a single Visit.
      b00489b3
  12. 08 Sep, 2023 2 commits
  13. 07 Sep, 2023 1 commit
  14. 06 Sep, 2023 3 commits
  15. 05 Sep, 2023 1 commit
  16. 31 Aug, 2023 2 commits