ONNXRuntime: update to version 1.25.1#10516
Open
smuzaffar wants to merge 2 commits intoIB/CMSSW_17_0_X/masterfrom
Open
ONNXRuntime: update to version 1.25.1#10516smuzaffar wants to merge 2 commits intoIB/CMSSW_17_0_X/masterfrom
smuzaffar wants to merge 2 commits intoIB/CMSSW_17_0_X/masterfrom
Conversation
Contributor
|
A new Pull Request was created by @smuzaffar for branch IB/CMSSW_17_0_X/master. @akritkbehera, @cmsbuild, @iarspider, @raoatifshad, @smuzaffar can you please review it and eventually sign? Thanks. |
Contributor
|
cms-bot internal usage |
Contributor
Author
|
please test |
Contributor
Author
|
@fwyzard , looks like newer version of ONNXRuntime (ORT) fails for cuda arch 60 (Pascal). It only fails for one ORT source file. For now in this PR I propose to build ORT with cuda 6.x support. |
Contributor
Author
|
please test for el9_amd64_gcc14 |
Contributor
|
+1 Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-0a93d4/52935/summary.html Comparison SummarySummary:
Max Memory Comparisons exceeding threshold@cms-sw/core-l2 , I found 42 workflow step(s) with memory usage exceeding the error threshold: Expand to see workflows ...
|
Contributor
|
-1 Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-0a93d4/52940/summary.html Failed External BuildI found compilation error when building: ++ mv /data/cmsbld/jenkins/workspace/ib-run-pr-tests/testBuildDir/BUILD/el9_amd64_gcc14/external/onnxruntime/1.25.1-67747e4c1218bf29cba2862949bd66ba/cuda_gcc_supported.txt /data/cmsbld/jenkins/workspace/ib-run-pr-tests/testBuildDir/tmp/cache/cuda_gcc_supported.txt
++ cat /data/cmsbld/jenkins/workspace/ib-run-pr-tests/testBuildDir/tmp/cache/cuda_gcc_supported.txt
+ '[' true = true ']'
+ USE_CUDA=ON
/data/cmsbld/jenkins/workspace/ib-run-pr-tests/testBuildDir/tmp/rpm-tmp.9OHiTp: line 69: syntax error near unexpected token `<<<'
error: Bad exit status from /data/cmsbld/jenkins/workspace/ib-run-pr-tests/testBuildDir/tmp/rpm-tmp.9OHiTp (%build)
RPM build warnings:
Macro expanded in comment on line 488: %{pkginstroot}/${PYTHON3_LIB_SITE_PACKAGES}
|
Contributor
We have not removed CUDA arch 6.0 from CMSSW (yet). Should we do that, then ? |
Contributor
Dropping 6.0 in general now makes sense to me. |
Contributor
|
OK, let's re-remove Pascal globally. |
Contributor
Author
|
please test with #10493 |
Contributor
|
Pull request #10516 was updated. |
Contributor
Author
|
please test with #10493 |
Contributor
|
+1 Summary: https://cmssdt.cern.ch/SDT/jenkins-artifacts/pull-request-integration/PR-0a93d4/52980/summary.html The following merge commits were also included on top of IB + this PR after doing git cms-merge-topic:
You can see more details here: Comparison SummarySummary:
Max Memory Comparisons exceeding threshold@cms-sw/core-l2 , I found 42 workflow step(s) with memory usage exceeding the error threshold: Expand to see workflows ...
|
Contributor
Author
|
enable gpu |
Contributor
Author
|
please test with #10493 |
Contributor
|
-1 Failed Tests: RelVals nvidia_l40sUnitTests The following merge commits were also included on top of IB + this PR after doing git cms-merge-topic: You can see more details here: Failed RelVals
Expand to see more relval errors ...
AMD_MI300X Comparison SummarySummary:
AMD_W7900 Comparison SummarySummary:
|
Contributor
Author
|
please test with #10493 |
Contributor
|
-1 Failed Tests: RelVals-AMD_MI300X Failed RelVals-AMD_MI300XThe relvals timed out after 4 hours. Comparison SummarySummary:
AMD_W7900 Comparison SummarySummary:
NVIDIA_H100 Comparison SummarySummary:
NVIDIA_L40S Comparison SummarySummary:
Max Memory Comparisons exceeding threshold@cms-sw/core-l2 , I found 42 workflow step(s) with memory usage exceeding the error threshold: Expand to see workflows ...
|
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
This PR updates ONNXRuntime to latest version v1.25.1.
60as compilation of https://github.com/microsoft/onnxruntime/blob/v1.25.1/onnxruntime/contrib_ops/cuda/quantization/matmul_8bits.cu failed with error [a] when cude arch 60 is used[a]