1. 12 Mar, 2020 1 commit
    • [Strategy] Support for Int8 schedules - CUDA/x86 (#5031) · 681df4fc
      * [CUDA] Op strategy changes for Int8 schedules.
      
      * Applying Haichen's suggestions.
      
      * Make 4D output work for task extraction.
      
      * Make x86 work.
      
      * Fix lint.
      
      * Lint fixes.
      
      * Tests, comments, out channel a multiple of 4.
      
      * Topi test.
      
      Co-authored-by: Ubuntu <ubuntu@ip-172-31-38-96.us-west-2.compute.internal>
      Animesh Jain committed
  2. 27 Feb, 2020 1 commit
  3. 15 Feb, 2020 1 commit
  4. 14 Feb, 2020 1 commit
  5. 12 Feb, 2020 1 commit
    • [REFACTOR][PY][API-CHANGE] establish tvm.ir, migrate corresponding files (#4862) · a5661611
      * [REFACTOR][PY][API-CHANGE] establish tvm.ir, migrate corresponding relay files.
      
      This PR establishes tvm.ir and migrates the corresponding relay
      files into the new folder.
      
      API Change:
      - relay.Module -> tvm.IRModule
      
      * Update with ADT
      
      * Migrate transform
      
      * address comments
      
      * Migrate module
      
      * Migrate json_compact
      
      * Migrate attrs
      
      * Move LoweredFunc to stmt temporarily
      
      * temp migrate container
      
      * Finish migrate container
      Tianqi Chen committed
  6. 03 Jan, 2020 1 commit
  7. 19 Nov, 2019 1 commit
  8. 16 Nov, 2019 1 commit
    • Retain qnn input kernel scales (#4292) · 3ba9dd09
      * Add qnn conv2d attributes for input_tensor_scale and
      kernel_tensor_scale.
      
      The lowering in the tflite frontend loses the input_tensor_scale
      and the kernel_tensor_scale by multiplying it and putting it into
      the Requantize operation. This means that any graph partitioning
      passes or other passes that need to access this information no longer
      have it available in the qnn dialect.
      
      regards
      Ramana
      
      * Store input tensor scale and Weight tensor scale for Dense as well
      
      As for conv2d, the tflite frontend drops the input tensor
      scale and the weight tensor scale from the relay op. Store
      it as separate fields in there.
      
      * Fix unintentional tab
      
      * Rename input_tensor_scale to input_scale and kernel_tensor_scale
      to kernel_scale for conv2d.
      
      * input_tensor_scale -> input_scale weight_tensor_scale->weight_scale
      
      * Rework dense testcase
      
      And use input_scale and kernel_scale
      
      * Be consistent in use of input_scale and kernel_scale values
      
      * Fixup qnn conv2d tests for input_scale and kernel_scale
      
      * Make pydoc identical between conv2d and dense for weight_tensor
      
      * Fix up conv2d parameters to be in the same order between C++ and python
      
      * Fix ordering of parameters for dense.
      
      * Add input_scale and output_scale to try and satisfy ci gods
      
      * Delete input_scale and kernel_scale.
      
      nn.conv2d does not contain input_scale and kernel_scale. We need
      to delete it when lowering it to nn.conv2d.
      
      * Add input_scale and kernel_scale for qnn.conv2d
      Ramana Radhakrishnan committed
  9. 13 Nov, 2019 1 commit
  10. 16 Sep, 2019 1 commit
  11. 30 Aug, 2019 1 commit