This is an automated email from the ASF dual-hosted git repository.
wuwei pushed a change to branch unity-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 155dd73ac6 Fix after merging 'main' into 'unity'
add 0b13b5c844 [Unity] Enhance Torch-consistency in rehsape (#16360)
add 8e54a9e91d [Unity][DLight] Introduce Specific Rule for RMSNorm (#16338)
add 4c77f0fc24 [TIR] Extend DP4A tensor intrin (#16293)
add 9caa179ce6 [CI] Update docker images tag to 20240105-165030-51bdaec6
(#16344)
add a1a1a7ca03 [AUTOTVM][FIX] Typo fixes and add a warning in the Droplet
Search (#16289)
new bf39afa04b Merge branch 'main' into unity
The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
Summary of changes:
ci/jenkins/docker-images.ini | 20 +-
ci/jenkins/generated/arm_jenkinsfile.groovy | 4 +-
ci/jenkins/generated/cortexm_jenkinsfile.groovy | 4 +-
ci/jenkins/generated/cpu_jenkinsfile.groovy | 4 +-
ci/jenkins/generated/docker_jenkinsfile.groovy | 4 +-
ci/jenkins/generated/gpu_jenkinsfile.groovy | 4 +-
ci/jenkins/generated/hexagon_jenkinsfile.groovy | 4 +-
ci/jenkins/generated/i386_jenkinsfile.groovy | 4 +-
ci/jenkins/generated/lint_jenkinsfile.groovy | 4 +-
.../generated/minimal_cross_isa_jenkinsfile.groovy | 4 +-
ci/jenkins/generated/minimal_jenkinsfile.groovy | 4 +-
ci/jenkins/generated/riscv_jenkinsfile.groovy | 4 +-
ci/jenkins/generated/wasm_jenkinsfile.groovy | 4 +-
ci/jenkins/templates/utils/base.groovy.j2 | 2 +-
include/tvm/topi/nn/rms_norm.h | 24 +-
python/tvm/autotvm/tuner/__init__.py | 1 +
.../tuner/{droplet_turner.py => droplet_tuner.py} | 17 +-
python/tvm/dlight/gpu/__init__.py | 1 +
python/tvm/dlight/gpu/rmsnorm.py | 140 ++++++++++
python/tvm/relax/frontend/nn/_tensor_op.py | 4 +-
python/tvm/tir/tensor_intrin/arm_cpu.py | 9 +-
python/tvm/tir/tensor_intrin/dot_product_common.py | 82 +++---
python/tvm/tir/tensor_intrin/rocm.py | 3 +-
src/target/source/codegen_cuda.cc | 2 +
src/target/source/literal/cuda_int8_t.h | 64 +++++
tests/python/dlight/test_gpu_rmsnorm.py | 287 +++++++++++++++++++++
tests/python/relax/test_frontend_nn_tensor.py | 10 +-
.../python/relax/test_transform_legalize_ops_nn.py | 100 ++++---
.../tir-schedule/test_tir_schedule_tensorize.py | 50 ++--
tests/scripts/task_show_node_info.sh | 1 +
30 files changed, 725 insertions(+), 140 deletions(-)
rename python/tvm/autotvm/tuner/{droplet_turner.py => droplet_tuner.py} (88%)
create mode 100644 python/tvm/dlight/gpu/rmsnorm.py
create mode 100644 src/target/source/literal/cuda_int8_t.h
create mode 100644 tests/python/dlight/test_gpu_rmsnorm.py
