This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch unity-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard d4c8f9bb0b [Unity][Op] Add ShapeExpr Tests for Reshape Op (#14035)
discard 590d446863 [Unity][Pass] Operator legalization (#14029)
discard d1d6cd784b [Unity][TVMScript] Move tir/relax import in script out of
__init__.py (#14033)
discard e97060fd23 [Unity][Pass] Wellformed Analysis (#14032)
discard 170827f634 [Unity][BlockBuilder] CallTE convert PrimValue args
(#14028)
discard d56e04c8cc [Unity][Pass] Normalize Pass (#14031)
discard 0bab3d400a [Unity] Relay -> Relax translator (#14026)
discard 54e15a94c7 [Unity][Pass][TuningAPI] Introduce TuningAPI and
MetaSchedule pass (#14014)
discard a48aa6bd7a [Unity][Pass] BindParams pass, FoldConstant pass (#14016)
discard 99eef364ef [Unity][VM] Supporting "compiled" exec mode. (#14015)
discard c1902faa0a [Unity][Pass] LambdaLift pass (#14012)
discard 3f385aba94 [Unity][Pass] Operator Fusion Passes (#14001)
discard d62e5b4419 [Unity] NestedMsg Support utility (#13995)
discard ad1f8ac70b [Unity] Relax op: manipulation (#13989)
discard d805689640 [Unity] Relax op: search (#13992)
discard 323e99ce93 [Unity] Relax op: linear algebra (#13988)
discard b2b9e1278d [Unity] Relax op: creation (#13984)
discard 8a04832e0e [Unity] Relax op: neural networks (#13993)
discard c30576168b [Unity] Relax op: statistical (#13991)
discard dbf121c293 [Unity] Relax op: arithmetic, comparison (#13983)
discard fcda9b6824 [Unity] Relax op: image (#13994)
discard 77a319e926 [Unity] Relax op: set (#13990)
discard 6ed1b4bf72 [Unity] Relax op: datatype (#13986)
discard e6292a197c [Unity] Relax op: index (#13987)
discard f197d45723 [Unity][TVMScript] Use explicit `R.shape` in TVMScript
(#13979)
discard a86cc11c23 [Unity] e2e Relax minimum build flow (#13961)
discard 998da7cf9c [Unity] Relax VM shape lowering pass (#13956)
discard 7dd45cc15e [Unity] Relax VM codegen (#13954)
discard eb026b74ea [Unity] Relax TVMScript Printer (#13944)
discard 66ffba8c95 [Unity] Relax TVMScript Parser. (#13932)
discard 98bb5282e5 [Unity] Relax BlockBuilder and ExprMutator (#13926)
discard 22d3ca5aff [Unity] Basic StructInfo Analysis and Expr construction
(#13916)
discard df06448690 [Unity][CI] Unity specific jenkins setup (do not upstream
to main) (#13910)
discard d3ee97dd19 [Unity][IR] First-class StructInfo (#13907)
discard 09a15d78b2 [Unity] Relax expressions and types (#13901)
discard 8bc90d5ae1 [Unity] Relax VM (#13878)
add 7249904622 [AutoScheduler][AutoTVM] Enable xgboost >= 1.7.x new
changes (#14036)
new adc73e35ca [Unity] Relax VM (#13878)
new 1528a8db87 [Unity] Relax expressions and types (#13901)
new d25251fb91 [Unity][IR] First-class StructInfo (#13907)
new 366c89d897 [Unity][CI] Unity specific jenkins setup (do not upstream
to main) (#13910)
new 4433f192bd [Unity] Basic StructInfo Analysis and Expr construction
(#13916)
new e824efe4ac [Unity] Relax BlockBuilder and ExprMutator (#13926)
new 1f7aed4236 [Unity] Relax TVMScript Parser. (#13932)
new d15126636a [Unity] Relax TVMScript Printer (#13944)
new 48a4f2d4e1 [Unity] Relax VM codegen (#13954)
new 3b79924383 [Unity] Relax VM shape lowering pass (#13956)
new a9a21ed988 [Unity] e2e Relax minimum build flow (#13961)
new bfa3b9c6d1 [Unity][TVMScript] Use explicit `R.shape` in TVMScript
(#13979)
new d3870a7229 [Unity] Relax op: index (#13987)
new baa08eec21 [Unity] Relax op: datatype (#13986)
new e561dd93db [Unity] Relax op: set (#13990)
new af46f0df85 [Unity] Relax op: image (#13994)
new 5e71c8060e [Unity] Relax op: arithmetic, comparison (#13983)
new e12a97e23c [Unity] Relax op: statistical (#13991)
new 25b1fae67d [Unity] Relax op: neural networks (#13993)
new e980513ad7 [Unity] Relax op: creation (#13984)
new 096f8464e9 [Unity] Relax op: linear algebra (#13988)
new 07dd06c3bf [Unity] Relax op: search (#13992)
new 9c4e7e3944 [Unity] Relax op: manipulation (#13989)
new 04d68873ed [Unity] NestedMsg Support utility (#13995)
new dca96539f8 [Unity][Pass] Operator Fusion Passes (#14001)
new 87a911f1c3 [Unity][Pass] LambdaLift pass (#14012)
new 617f21e260 [Unity][VM] Supporting "compiled" exec mode. (#14015)
new a4dc336bd3 [Unity][Pass] BindParams pass, FoldConstant pass (#14016)
new dcb6ae9786 [Unity][Pass][TuningAPI] Introduce TuningAPI and
MetaSchedule pass (#14014)
new 53b3dc82a0 [Unity] Relay -> Relax translator (#14026)
new 16e0c5f064 [Unity][Pass] Normalize Pass (#14031)
new 001a414484 [Unity][BlockBuilder] CallTE convert PrimValue args
(#14028)
new 407e7f43b6 [Unity][Pass] Wellformed Analysis (#14032)
new 8ca086b227 [Unity][TVMScript] Move tir/relax import in script out of
__init__.py (#14033)
new d789a293f5 [Unity][Pass] Operator legalization (#14029)
new e06d67213e [Unity][Op] Add ShapeExpr Tests for Reshape Op (#14035)
new cd55803ae1 [Unity] Initial PyTorch Frontend (#14037)
new e0775c8c95 [Unity][Pass] Block-level static memory planning (#14038)
new 50bcd1b0af [Unity] Disallow inline prim_func in relax IR (#14040)
new b42f8a44cd [Unity] Update tests to adapt to latest TVMScript syntax
(#14039)
new 413329dfa2 [Unity] Relax dataflow pattern language (matching) (#14041)
new 7e4d71cc1e [Unity] Statement rewriter for DataflowBlock (#14043)
This update added new revisions after undoing existing revisions.
That is to say, some revisions that were in the old version of the
branch are not in the new version. This situation occurs
when a user --force pushes a change and generates a repository
containing something like this:
* -- * -- B -- O -- O -- O (d4c8f9bb0b)
\
N -- N -- N refs/heads/unity-staging (7e4d71cc1e)
You should already have received notification emails for all of the O
revisions, and so the following emails describe only the N revisions
from the common base, B.
Any revisions marked "omit" are not gone; other references still
refer to them. Any revisions marked "discard" are gone forever.
The 42 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:
docs/install/from_source.rst | 4 +-
include/tvm/relax/analysis.h | 56 +
include/tvm/relax/binding_rewrite.h | 115 ++
include/tvm/relax/dataflow_matcher.h | 80 +
include/tvm/relax/dataflow_pattern.h | 810 +++++++++
.../{relay => relax}/dataflow_pattern_functor.h | 89 +-
include/tvm/relax/transform.h | 9 +
include/tvm/relax/utils.h | 1 +
python/gen_requirements.py | 2 +-
python/tvm/auto_scheduler/cost_model/xgb_model.py | 202 ++-
python/tvm/autotvm/tuner/xgboost_cost_model.py | 201 ++-
python/tvm/relax/__init__.py | 3 +
python/tvm/relax/analysis/__init__.py | 1 +
python/tvm/relax/analysis/analysis.py | 59 +-
python/tvm/relax/analysis/estimate_memory_usage.py | 164 ++
python/tvm/relax/binding_rewrite.py | 155 ++
.../_template => python/tvm/relax/dpl}/__init__.py | 7 +-
.../{relay/dataflow_pattern => relax/dpl}/_ffi.py | 2 +-
python/tvm/relax/dpl/context.py | 86 +
python/tvm/relax/dpl/pattern.py | 1095 +++++++++++++
.../tvm/relax/frontend}/__init__.py | 5 +-
.../tvm/relax/frontend/torch}/__init__.py | 7 +-
python/tvm/relax/frontend/torch/dynamo.py | 156 ++
python/tvm/relax/frontend/torch/fx_translator.py | 817 +++++++++
python/tvm/relax/pipeline.py | 84 +
python/tvm/relax/transform/transform.py | 11 +
python/tvm/relax/vm.py | 1 +
python/tvm/script/parser/relax/parser.py | 10 +
src/relax/analysis/udchain.cc | 102 ++
src/relax/analysis/var2value.cc | 91 ++
src/relax/analysis/well_formed.cc | 6 +-
src/relax/ir/binding_rewrite.cc | 324 ++++
src/relax/ir/block_builder.cc | 22 -
src/relax/ir/dataflow_matcher.cc | 768 +++++++++
src/relax/ir/dataflow_matcher_impl.h | 87 +
src/relax/ir/dataflow_pattern.cc | 607 +++++++
.../ir/dataflow_pattern_functor.cc | 44 +-
src/relax/transform/static_plan_block_memory.cc | 750 +++++++++
tests/python/relax/test_analysis.py | 139 +-
.../relax/test_analysis_estimate_memory_usage.py | 125 ++
tests/python/relax/test_analysis_well_formed.py | 36 +
tests/python/relax/test_binding_rewrite.py | 334 ++++
tests/python/relax/test_dataflow_pattern.py | 867 ++++++++++
tests/python/relax/test_frontend_dynamo.py | 198 +++
tests/python/relax/test_frontend_from_fx.py | 1729 ++++++++++++++++++++
.../python/relax/test_pipeline.py | 36 +-
tests/python/relax/test_transform.py | 6 +-
.../test_transform_annotate_tir_op_pattern.py | 6 +-
.../relax/test_transform_attach_global_symbol.py | 16 +-
tests/python/relax/test_transform_fold_constant.py | 24 +-
tests/python/relax/test_transform_lambda_lift.py | 10 +-
.../relax/test_transform_legalize_ops_binary.py | 264 +--
.../test_transform_legalize_ops_create_datatype.py | 120 +-
.../relax/test_transform_legalize_ops_image.py | 28 +-
..._transform_legalize_ops_index_linear_algebra.py | 54 +-
.../test_transform_legalize_ops_manipulate.py | 142 +-
.../python/relax/test_transform_legalize_ops_nn.py | 154 +-
...st_transform_legalize_ops_search_statistical.py | 106 +-
.../relax/test_transform_legalize_ops_unary.py | 120 +-
.../relax/test_transform_meta_schedule_tuning.py | 2 +-
tests/python/relax/test_transform_normalize.py | 2 +-
.../test_transform_static_plan_block_memory.py | 612 +++++++
tests/python/relax/test_tuning_api.py | 2 +-
tests/python/relax/test_tvmscript_ir_builder.py | 4 +-
tests/python/relax/test_tvmscript_parser.py | 87 +-
tests/python/relax/test_vm_build.py | 22 +-
66 files changed, 11412 insertions(+), 866 deletions(-)
create mode 100644 include/tvm/relax/binding_rewrite.h
create mode 100644 include/tvm/relax/dataflow_matcher.h
create mode 100644 include/tvm/relax/dataflow_pattern.h
copy include/tvm/{relay => relax}/dataflow_pattern_functor.h (65%)
create mode 100644 python/tvm/relax/analysis/estimate_memory_usage.py
create mode 100644 python/tvm/relax/binding_rewrite.py
copy {apps/uma/_template => python/tvm/relax/dpl}/__init__.py (89%)
copy python/tvm/{relay/dataflow_pattern => relax/dpl}/_ffi.py (93%)
create mode 100644 python/tvm/relax/dpl/context.py
create mode 100644 python/tvm/relax/dpl/pattern.py
copy {apps/uma/_template => python/tvm/relax/frontend}/__init__.py (92%)
copy {apps/uma/_template => python/tvm/relax/frontend/torch}/__init__.py (82%)
create mode 100644 python/tvm/relax/frontend/torch/dynamo.py
create mode 100644 python/tvm/relax/frontend/torch/fx_translator.py
create mode 100644 python/tvm/relax/pipeline.py
create mode 100644 src/relax/analysis/udchain.cc
create mode 100644 src/relax/analysis/var2value.cc
create mode 100644 src/relax/ir/binding_rewrite.cc
create mode 100644 src/relax/ir/dataflow_matcher.cc
create mode 100644 src/relax/ir/dataflow_matcher_impl.h
create mode 100644 src/relax/ir/dataflow_pattern.cc
copy src/{relay => relax}/ir/dataflow_pattern_functor.cc (75%)
create mode 100644 src/relax/transform/static_plan_block_memory.cc
create mode 100644 tests/python/relax/test_analysis_estimate_memory_usage.py
create mode 100644 tests/python/relax/test_binding_rewrite.py
create mode 100644 tests/python/relax/test_dataflow_pattern.py
create mode 100644 tests/python/relax/test_frontend_dynamo.py
create mode 100644 tests/python/relax/test_frontend_from_fx.py
copy python/tvm/relax/ir/instrument.py => tests/python/relax/test_pipeline.py
(52%)
create mode 100644
tests/python/relax/test_transform_static_plan_block_memory.py
