[WIP] Ship BR schema as standalone llmdbenchmark-schema package

[Bslabe123]

Summary

Splits the Benchmark Report (BR) schema types out of the main llmdbenchmark distribution and into a separate pip-installable package, llmdbenchmark-schema, living in the same repo under llmdbenchmark-schema/.

External tools that produce or consume BR reports (workload generators like inference-perf, dashboards, analysis pipelines) currently have to either vendor the schema files or pull in the full llmdbenchmark package, which carries kubernetes, pykube-ng, kubernetes-asyncio, transformers, huggingface_hub, etc. Those deps are unrelated to the schema and don't belong in the dependency closure of a typed schema consumer.

After this change:

• pip install llmdbenchmark-schema pulls in only pydantic>=2.0 and PyYAML.
• pip install llmdbenchmark continues to work and re-exports the schema types under llmdbenchmark.analysis.benchmark_report, existing callers do not need to change.
• Both distributions ship from the same repo, the same commit, the same maintainers, the same CI workflow.

Marked WIP because the publish workflow still needs to be updated to push both distributions from the same CI run (see open questions below). The code split itself is complete and locally verified.

Layout

llmdbenchmark-schema/
  pyproject.toml                            # name = "llmdbenchmark-schema"
  README.md
  llmdbenchmark_schema/
    __init__.py
    base.py                                 # moved from analysis/benchmark_report/
    schema_v0_1.py                          # moved
    schema_v0_2.py                          # moved
    schema_v0_2_components.py               # moved
    br_v0_1_example.yaml                    # moved
    br_v0_2_example.yaml                    # moved
    br_v0_1_json_schema.json                # moved
    br_v0_2_json_schema.json                # moved
    py.typed
llmdbenchmark/
  analysis/
    benchmark_report/
      __init__.py                           # re-exports from llmdbenchmark_schema
      cli.py, core.py, native_to_br0_*.py   # import from llmdbenchmark_schema
pyproject.toml                              # adds llmdbenchmark-schema as a dep

History is preserved via git mv so blame and per-file history follow the files to their new location.

Verified locally

• pip install -e llmdbenchmark-schema/ succeeds.
• from llmdbenchmark_schema import BenchmarkReportV02 works.
• The vendored br_v0_2_example.yaml round-trips against BenchmarkReportV02.
• All updated files under llmdbenchmark/analysis/benchmark_report/ compile cleanly with the new import paths.

Open questions for reviewers

• Update the publish workflow to push both llmdbenchmark and llmdbenchmark-schema to PyPI from the same CI run.
• Sweep the repo for any other places still doing relative imports of the moved files. I rewrote the ones I found in llmdbenchmark/analysis/benchmark_report/; happy to look at more if reviewers point them out.
• Naming: llmdbenchmark-schema (PyPI name) and llmdbenchmark_schema (Python package). Open to bikeshed.

Motivation

kubernetes-sigs/inference-perf#461 currently vendors ~1,300 lines of the BR0.2 schema from this repo because there's no other way to consume the types. With this change, that PR can replace the vendored files with llmdbenchmark-schema as a pip dependency.

Filing this WIP as a starting point for discussion; happy to iterate on the structure, naming, or split boundary.