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 6ea9afc408 [Unity] Refactor Relax Build JIT UX (#14088)
discard d0caea5986 [Unity][Fix][Pass] FoldConstant with DCE in dataflow block
(#14087)
discard dc4c75bb28 [Unity][Analysis] TIR pattern kind analysis for
multi-buffer write block (#14075)
discard 7544cf6869 [Unity][Op] `log_softmax` and `cross_entropy_with_logits`
(#14083)
discard 9607b3f974 [Unity][BYOC] Add DNNL backend (#14082)
discard 561bd88684 [Unity][BYOC] Add CUTLASS backend (#14081)
discard 068e52096a [Unity] Add testcases for `expr_args_converter` (#14080)
discard ae4ed43d5a [Unity][Pass] Canonicalize Bindings (#14079)
discard 825bb8125d [Unity][BYOC][Pass] RunCodegen and TensorRT (#14078)
discard 8f8c3f0474 [Unity][Transform] Add LiftTransformParams pass (#14069)
discard 77c763f251 [Unity][Frontend] Annotate number of non-static input of FX
function (#14067)
discard 46ebe80819 [Unity][BYOC] Add pass to merge composite functions to
offload large subgraphs (#14062)
discard bf2f8118df [Unity][Pass] Remove Unused Function (#14061)
discard dd6431e863 [Unity][Fix][Pass] Fix FuseOps for lack graph edges (#14058)
discard f93a50c2d0 [Unity] Relax op: collapse sum (#14059)
discard 511112b173 [Unity][BYOC] Add pattern-based partitioning pass (#14054)
discard ee98cd4511 [Unity][VM] Add per-op profiling support (#14053)
discard a32cde1fa0 [Unity][TVMScript] Overload `__neg__` for relax expr
(#14045)
discard 7f8d0e9bfb [Unity][Pass] FuseOps FuseTIR fixes (#14044)
discard fe2110febc [Unity] Statement rewriter for DataflowBlock (#14043)
discard 3ae748f3a9 [Unity] Relax dataflow pattern language (matching) (#14041)
discard 970d2148ba [Unity] Update tests to adapt to latest TVMScript syntax
(#14039)
discard e9a57c562c [Unity] Disallow inline prim_func in relax IR (#14040)
discard c2b4ad1c8c [Unity][Pass] Block-level static memory planning (#14038)
discard b78ae86324 [Unity] Initial PyTorch Frontend (#14037)
discard add20d325f [Unity][Op] Add ShapeExpr Tests for Reshape Op (#14035)
discard 17bebf65ea [Unity][Pass] Operator legalization (#14029)
discard 8c6437e92f [Unity][TVMScript] Move tir/relax import in script out of
__init__.py (#14033)
discard c251c4ba7c [Unity][Pass] Wellformed Analysis (#14032)
discard 731292b6da [Unity][BlockBuilder] CallTE convert PrimValue args
(#14028)
discard e997c676ce [Unity][Pass] Normalize Pass (#14031)
discard 40fa1d39fe [Unity] Relay -> Relax translator (#14026)
discard e5b13d8982 [Unity][Pass][TuningAPI] Introduce TuningAPI and
MetaSchedule pass (#14014)
discard 0e948d84bd [Unity][Pass] BindParams pass, FoldConstant pass (#14016)
discard 122521b68c [Unity][VM] Supporting "compiled" exec mode. (#14015)
discard 5a63ff7e85 [Unity][Pass] LambdaLift pass (#14012)
discard 59dfc38765 [Unity][Pass] Operator Fusion Passes (#14001)
discard a7c5975be8 [Unity] NestedMsg Support utility (#13995)
discard 37bb48acca [Unity] Relax op: manipulation (#13989)
discard eb7b829230 [Unity] Relax op: search (#13992)
discard 6c64a29c61 [Unity] Relax op: linear algebra (#13988)
discard 070e1ae6c4 [Unity] Relax op: creation (#13984)
discard 95f609df68 [Unity] Relax op: neural networks (#13993)
discard cf5468bc24 [Unity] Relax op: statistical (#13991)
discard 1cab6af7f4 [Unity] Relax op: arithmetic, comparison (#13983)
discard 18d0dc23de [Unity] Relax op: image (#13994)
discard 20b3436e8a [Unity] Relax op: set (#13990)
discard 4d12d68943 [Unity] Relax op: datatype (#13986)
discard e0f59c7f75 [Unity] Relax op: index (#13987)
discard 36e41e1211 [Unity][TVMScript] Use explicit `R.shape` in TVMScript
(#13979)
discard 2ac2d04f38 [Unity] e2e Relax minimum build flow (#13961)
discard f4f0057500 [Unity] Relax VM shape lowering pass (#13956)
discard 27ac65fd84 [Unity] Relax VM codegen (#13954)
discard 6b8b04243a [Unity] Relax TVMScript Printer (#13944)
discard 79de7f4995 [Unity] Relax TVMScript Parser. (#13932)
discard b758112b5b [Unity] Relax BlockBuilder and ExprMutator (#13926)
discard 9449f7fc24 [Unity] Basic StructInfo Analysis and Expr construction
(#13916)
discard 071c9de0ea [Unity][CI] Unity specific jenkins setup (do not upstream
to main) (#13910)
discard a485a1dcad [Unity][IR] First-class StructInfo (#13907)
discard 70dfbb3783 [Unity] Relax expressions and types (#13901)
discard 2f9650f648 [Unity] Relax VM (#13878)
new 9c5d8cdbe4 [Unity] Relax VM (#13878)
new 57a4103f90 [Unity] Relax expressions and types (#13901)
new 3cf1cd9c16 [Unity][IR] First-class StructInfo (#13907)
new 687a18682d [Unity][CI] Unity specific jenkins setup (do not upstream
to main) (#13910)
new b280cee321 [Unity] Basic StructInfo Analysis and Expr construction
(#13916)
new 96a2cd9265 [Unity] Relax BlockBuilder and ExprMutator (#13926)
new f08beac336 [Unity] Relax TVMScript Parser. (#13932)
new 349c384a06 [Unity] Relax TVMScript Printer (#13944)
new aedf8dca02 [Unity] Relax VM codegen (#13954)
new b78e16f46a [Unity] Relax VM shape lowering pass (#13956)
new 1ef1f468ee [Unity] e2e Relax minimum build flow (#13961)
new b77f0876b1 [Unity][TVMScript] Use explicit `R.shape` in TVMScript
(#13979)
new 60688afedd [Unity] Relax op: index (#13987)
new 052310f0f7 [Unity] Relax op: datatype (#13986)
new 5324769aef [Unity] Relax op: set (#13990)
new a6ca1d53c8 [Unity] Relax op: image (#13994)
new 303d2da270 [Unity] Relax op: arithmetic, comparison (#13983)
new ce4c3a4e31 [Unity] Relax op: statistical (#13991)
new 2b801849c9 [Unity] Relax op: neural networks (#13993)
new 430299a0a3 [Unity] Relax op: creation (#13984)
new 0e11e439f9 [Unity] Relax op: linear algebra (#13988)
new e4a1e42fac [Unity] Relax op: search (#13992)
new f72667a6b8 [Unity] Relax op: manipulation (#13989)
new 386bbe48be [Unity] NestedMsg Support utility (#13995)
new 32f4767876 [Unity][Pass] Operator Fusion Passes (#14001)
new 39efa6e49c [Unity][Pass] LambdaLift pass (#14012)
new 74b00364b6 [Unity][VM] Supporting "compiled" exec mode. (#14015)
new 7558950af0 [Unity][Pass] BindParams pass, FoldConstant pass (#14016)
new 545bce5330 [Unity][Pass][TuningAPI] Introduce TuningAPI and
MetaSchedule pass (#14014)
new e784acd9cb [Unity] Relay -> Relax translator (#14026)
new ecd8cf9c24 [Unity][Pass] Normalize Pass (#14031)
new 49bf8992f7 [Unity][BlockBuilder] CallTE convert PrimValue args
(#14028)
new 7daf1ed5ab [Unity][Pass] Wellformed Analysis (#14032)
new 1dfcdafe0a [Unity][TVMScript] Move tir/relax import in script out of
__init__.py (#14033)
new 83e34aadd1 [Unity][Pass] Operator legalization (#14029)
new cfcdd607b1 [Unity][Op] Add ShapeExpr Tests for Reshape Op (#14035)
new 7b959411b9 [Unity] Initial PyTorch Frontend (#14037)
new e430b063b9 [Unity][Pass] Block-level static memory planning (#14038)
new 6c2e331376 [Unity] Disallow inline prim_func in relax IR (#14040)
new a6134ce966 [Unity] Update tests to adapt to latest TVMScript syntax
(#14039)
new 251a4afc1d [Unity] Relax dataflow pattern language (matching) (#14041)
new 4bcad0bd0b [Unity] Statement rewriter for DataflowBlock (#14043)
new 2376c0b948 [Unity][Pass] FuseOps FuseTIR fixes (#14044)
new 9816f4742d [Unity][TVMScript] Overload `__neg__` for relax expr
(#14045)
new b95f8b0a81 [Unity][VM] Add per-op profiling support (#14053)
new bf6f86dd44 [Unity][BYOC] Add pattern-based partitioning pass (#14054)
new 33bd494554 [Unity] Relax op: collapse sum (#14059)
new 529023cabd [Unity][Fix][Pass] Fix FuseOps for lack graph edges (#14058)
new c84ce57ced [Unity][Pass] Remove Unused Function (#14061)
new 0ebc0a23af [Unity][BYOC] Add pass to merge composite functions to
offload large subgraphs (#14062)
new 9c67d76b34 [Unity][Frontend] Annotate number of non-static input of FX
function (#14067)
new ffb96a88d6 [Unity][Transform] Add LiftTransformParams pass (#14069)
new c60bcc29be [Unity][BYOC][Pass] RunCodegen and TensorRT (#14078)
new bb36fb33ee [Unity][Pass] Canonicalize Bindings (#14079)
new 98d3db33f0 [Unity] Add testcases for `expr_args_converter` (#14080)
new 6425d27c01 [Unity][BYOC] Add CUTLASS backend (#14081)
new 4a6559c4c0 [Unity][BYOC] Add DNNL backend (#14082)
new 750f81c0a2 [Unity][Op] `log_softmax` and `cross_entropy_with_logits`
(#14083)
new bab3bc6de4 [Unity][Analysis] TIR pattern kind analysis for
multi-buffer write block (#14075)
new 8d5181a535 [Unity][Fix][Pass] FoldConstant with DCE in dataflow block
(#14087)
new 1ff7188079 [Unity] Refactor Relax Build JIT UX (#14088)
new 37a38a5dc0 [Unity][Relax] Set Shape Function to Be Host Function
(#14090)
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 (6ea9afc408)
\
N -- N -- N refs/heads/unity-staging (37a38a5dc0)
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 62 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:
src/relax/backend/vm/vm_shape_lower.cc | 5 +++++
tests/python/relax/test_backend_transform_shape_lower.py | 1 +
2 files changed, 6 insertions(+)
