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

Posted to commits@tvm.apache.org by jc...@apache.org on 2021/04/14 02:10:34 UTC

[tvm] branch main updated (ce86454 -> 90dce48)

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

jcf94 pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.


    from ce86454  [RUNTIME] Add clear() function in tvm::Map class (#7826)
     add 90dce48  [Topi & Relay] Add quantization support for the vision transform model in GPU (#7814)

No new revisions were added by this update.

Summary of changes:
 include/tvm/relay/attrs/nn.h                       |   8 +-
 python/tvm/relay/op/nn/nn.py                       |   7 +-
 python/tvm/relay/op/strategy/cuda.py               |  21 ++-
 python/tvm/relay/op/strategy/generic.py            |   4 +-
 python/tvm/relay/quantize/_annotate.py             |  25 ++++
 python/tvm/relay/quantize/_calibrate.py            |  28 ++++
 python/tvm/topi/cuda/batch_matmul.py               | 147 ++++++++++++++++++++
 python/tvm/topi/testing/batch_matmul.py            |  12 +-
 src/relay/op/make_op.h                             |   2 +-
 src/relay/op/nn/nn.cc                              |   9 +-
 src/relay/quantize/realize.cc                      |  35 +++++
 .../transforms/combine_parallel_batch_matmul.cc    |  12 +-
 src/relay/transforms/combine_parallel_dense.cc     |   4 +-
 .../test_quantization_accuracy_for_vit.py          | 148 +++++++++++++++++++++
 tests/python/relay/test_pass_auto_quantize.py      |  32 +++++
 tests/python/topi/python/test_topi_batch_matmul.py |  53 ++++++++
 16 files changed, 528 insertions(+), 19 deletions(-)
 create mode 100644 tests/python/nightly/quantization/test_quantization_accuracy_for_vit.py