jpata/particleflow: v1.8.0

What's Changed

The focus of this release is training on CMS datasets. The model has been retrained on high-statistics CMS samples and outperforms the baseline in our MLPF samples. The export of the transformer model to ONNX works with Flash Attention, and it can be integrated with CMSSW 14 and run on GPU. We have run the first physics validations in CMSSW, and we find that the performance with respect to the previous CMS version of MLPF is improved, but it does not yet outperform the baseline PF in CMSSW.

Some slides from the CMS progress:

• https://indico.cern.ch/event/1399778/#2-cms-status
• https://indico.cern.ch/event/1415765/#2-cms-status-and-plans
• https://indico.cern.ch/event/1421798/#2-cms-status-and-plans-virtual
• https://indico.cern.ch/event/1426959/#2-cms-status-and-plans

The full list of PRs:

• Remove pytorch geometric by @jpata in https://github.com/jpata/particleflow/pull/310
• add new paper to README by @jpata in https://github.com/jpata/particleflow/pull/312
• Add Ray Train training to GitHub actions CI/CD test by @erwulff in https://github.com/jpata/particleflow/pull/314
• CMSSW documentation by @jpata in https://github.com/jpata/particleflow/pull/319
• Full CMS pytorch training in May 2024 by @jpata in https://github.com/jpata/particleflow/pull/316
• update CMSSW validation scripts and documentation by @jpata in https://github.com/jpata/particleflow/pull/322
• onnx export with dynamic shapes, fast attention by @jpata in https://github.com/jpata/particleflow/pull/324
• switch ONNX model to full float for CMSSW compatibility by @jpata in https://github.com/jpata/particleflow/pull/325
• Update validation scripts to CMSSW_14_1_0 by @jpata in https://github.com/jpata/particleflow/pull/323
• update cmssw plots, add ttbar sample to valid, add multiparticlegun and vbf to training by @jpata in https://github.com/jpata/particleflow/pull/330

Full Changelog: https://github.com/jpata/particleflow/compare/v1.7.0...v1.8.0