-
Notifications
You must be signed in to change notification settings - Fork 325
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Update onnx-mlir product version #1727
Merged
Changes from all commits
Commits
Show all changes
56 commits
Select commit
Hold shift + click to select a range
82606f1
Update onnx-mlir product version
MegoHam21 b50eb9d
fix einsum decomposition bug (#1730)
sorenlassen 95f7510
Update version to 0.3.1 (#1728)
cjvolzka a8e9bac
Fix issues to compile Yolov3-12. (#1726)
negiyas b0a54fa
simplified if lowering (#1717)
sorenlassen 4aa1523
Add definitions
MegoHam21 99f6afb
parse string type from getTypeMap() (#1735)
sorenlassen 4ae32e2
fix 2 compiler warnings (#1736)
sorenlassen bc1977b
cleanup some include files (#1733)
sorenlassen af5ba86
Fix remaining warnings on Windows and turn on warning-as-error (#1706)
sstamenova 75e8f86
Fix synax
MegoHam21 f501206
Simplify shape-related operations (#1695)
tungld 5f738fc
run-onnx-lib script and docs fixes (#1705)
sorenlassen d091ea8
remove initializedTensors map from ONNX parser (#1739)
sorenlassen f8a5b51
Add decompositions for v11 split, squeeze, and unsqueeze (#1702)
philass 8915187
factored input shaping into ModelInputShaper (#1740)
sorenlassen 68c356b
Ingest all of Opset 16 (#1704)
philass 5427f8b
Fix onnx-mlir.py docker wrapper (#1734)
gongsu832 cfacf7f
Update protobuf (#1747)
cjvolzka 8ef7e28
Add the product version and fix formatting
MegoHam21 dcddaa7
Make updates to product version
MegoHam21 d12930a
further updates
MegoHam21 4274752
Add product version text file
MegoHam21 bac7a7e
Removed the memory leaks directly in execution session (#1746)
AlexandreEichenberger a6550e0
Add support for ArgMin (#1737)
airMeng 5b6254b
Inclusive terminology update (#1750)
cjvolzka 31aa0cd
Warning and instructions that --onnx-op-stats needs more than EmitONN…
AlexandreEichenberger 0e11093
Move product version text file
MegoHam21 7127e69
Remove comment
MegoHam21 1bfaca2
Output the product version for the compiler/version
MegoHam21 fa613a7
Cleaned up commit of the InferTypes change. (#1753)
messerb5467 b4e2989
setup.py install is deprecated, use pip install instead (#1752)
gongsu832 1e028ad
adding reference to onnx-mlir-serving (#1745)
AlexandreEichenberger 369e015
[TOSA] Update type converter and unary ops (#1553)
e9306d5
Fix syntax
MegoHam21 9f5c7dd
Remove strip
MegoHam21 9a003ab
Revert "Cleaned up commit of the InferTypes change. (#1753)"
MegoHam21 6ca91f7
Cleaned up commit of the InferTypes change. (#1753)
messerb5467 23d210c
Fix for GatherND verifier (#1754)
philass fe5600b
Fix OnnxBuilder::concat where axis was not used (#1759)
tungld 3e4f8bb
Simplify GatherOp when its inputs are dimensions (#1755)
tungld bdd68b5
Assign each question mark a unique negative integer value (#1757)
tungld a9cf18c
Change the regex
MegoHam21 8008125
Fix regex and display product numbers
MegoHam21 9d2e6dc
normalize axis in ScatterElements verify (#1760)
philass e604d7e
redo ArrayRefOrSmallVector with enable_if (#1758)
sorenlassen 58c1063
fix syntax
MegoHam21 0893ac2
Handle scalar tensor tensor<type> in SimplifyShapeRelatesOps pass (#1…
tungld 9e00f74
namespace cleanup (#1763)
sorenlassen e78b1d5
Merge branch 'main' into hamptonm/feature/cmake
hamptonm1 3a4e261
Signed-off-by: Megan Hampton <[email protected]>
MegoHam21 5c3b6f9
Merge branch 'main' into hamptonm/feature/cmake
hamptonm1 dff0fba
Make use of the product vendor flag
MegoHam21 8867893
Merge branch 'main' into hamptonm/feature/cmake
hamptonm1 d024a57
Address feedback
MegoHam21 fb87d3f
Merge branch 'onnx:main' into hamptonm/feature/cmake
hamptonm1 File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Aren't
PRODUCT_VERSION_MAJOR
,PRODUCT_VERSION_MINOR
, andPRODUCT_VERSION_PATCH
andPRODUCT_ID
built by splitting apart theONNX_MLIR_PRODUCT_VERSION
supplied at compile time? If so, is there a reason to not useONNX_MLIR_PRODUCT_VERSION
directly instead of rebuilding it from the composite components here?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes there is a reason... if I attempt to use
ONNX_MLIR_PRODUCT_VERSION
it will fail on thecmake
command with the following error:I tried 3 times....so adding the code the way I did gets around this problem :)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Also I am not rebuilding it.... ONNX_MLIR_PRODUCT_VERSION is broken up into these 4 segments by using a
CMAKE_MATCH_1
and then a SET which was already added to the code.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ok. I thought that might be the case but I wanted to make sure. PR looks good to me. I'd say give it overnight to see if there's any other comments from other timezones but otherwise it's good to go.