Unified data exchange protocol across modules

[wheresmyhair]

This PR introduces a unified data exchange protocol as a pilot implementation, enabling batch operations and improving developer experience.

[wheresmyhair]

Comments on force-pushes: removed some personal info

[research4pan]

LGTM. Support unified data protocol for inference purposes (support sglang first for now).

Main Features

• Support unified data protocol DataProto for sglang (vllm not implemented yet)
  • src/lmflow/models/hf_decoder_model.py
    • lines 450: use "sampling_params" in inputs, allowing compatibility with vllm sampling params
  • src/lmflow/pipeline/sglang_inferencer.py
  • src/lmflow/utils/protocol.py

Details

• Change --save_results argument to --save_inference_results, --save_results argument will be deprecated in future versions (still supported in this version)

  • examples/rm_inference.py
  • scripts/archive/run_rm_inference.sh
  • scripts/archive/run_vllm_inference.sh
  • scripts/run_sglang_inference.sh: lines 11-12
  • src/lmflow/args.py
  • src/lmflow/pipeline/sglang_inferencer.py

• Change default dataset example in scripts/run_sglang_inference.sh (line 3)

• Change save format from json to pkl

  • src/lmflow/pipeline/sglang_inferencer.py

• Add tensordict to requirements.txt

• Add useful util functions in src/lmflow/utils/envs.py

• Improve README.md

• Improve gitignore

Suggestions

• src/lmflow/pipeline/sglang_inferencer.py, line 104-106: better support json-format output as well, since pkl is normally not human-readable