You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@tvm.apache.org by gi...@apache.org on 2022/12/14 05:02:39 UTC

[tvm] branch nightly updated (51431d5a8c -> c547bbb13d)

This is an automated email from the ASF dual-hosted git repository.

github-bot pushed a change to branch nightly
in repository https://gitbox.apache.org/repos/asf/tvm.git


    from 51431d5a8c [Relay] Bug fix in relay.squeeze function for issue #12400 (#12684)
     add ec9fcc0dac [Relay] Fix `CombineParallelDense` slicing axis  (#13597)
     add b7015bb388 [Fix] Task scheduler error prompt upon build/run failure (#13601)
     add 1d9863470e [TIR] Fix PlanAndUpdateBufferAllocationLocation not visiting constant buffer (#13605)
     add 12311dcdef [Hexagon] Enable depthwise conv2d NHWC with an HWIO kernel layout (#13414)
     add c547bbb13d [Relay][Frontend][Onnx] SequenceAt and SplitToSequence Operators (#13602)

No new revisions were added by this update.

Summary of changes:
 python/tvm/relay/frontend/onnx.py                  | 79 ++++++++++++++++++++++
 python/tvm/relay/op/_transform.py                  |  2 -
 python/tvm/relay/op/strategy/arm_cpu.py            |  2 +-
 python/tvm/relay/op/strategy/hexagon.py            |  3 +-
 python/tvm/relay/op/strategy/x86.py                |  3 +-
 python/tvm/topi/nn/depthwise_conv2d.py             | 19 +++++-
 src/meta_schedule/task_scheduler/task_scheduler.cc |  4 +-
 src/relay/transforms/combine_parallel_dense.cc     | 43 ++++++++----
 .../plan_update_buffer_allocation_location.cc      | 19 ++++--
 tests/python/frontend/onnx/test_forward.py         | 31 +++++----
 .../relay/test_pass_combine_parallel_dense.py      | 51 ++++++++++++--
 11 files changed, 209 insertions(+), 47 deletions(-)