Adding ParticleNet files in structure needed for SONIC #48
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Outdated suggestions cannot be applied.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 is a companion PR to cms-sw/cmssw#37964. We are adding a SONIC producer for ParticleNet (AK4, AK8 General, Mass Decorrelation, and MassRegression) to CMSSW to do some production tests. Nominally SONIC is designed to enable easy use of co-processors in CMS workflows, but it can also start up CPU-based inference servers within jobs. This PR does not affect any workflow in CMS in any way unless called specifically (the SONIC producer is independent of the generic ParticleNet one). The SONIC framework requires the model files and a specifically formatted config file for the Triton server, and these are contained in this PR in the structure required by NVIDIA Triton. Please refer to these slides for more information about SONIC and our use of NVIDIA Triton: https://indico.cern.ch/event/1143469/contributions/4799423/attachments/2416540/4135308/March_28_JetMET_SONIC.pdf. Note that both ONNX and PyTorch versions of the models are included - SONIC greatly simplifies the running of PyTorch models for CMS