CHANGELOG.md
CONTRIBUTING.md
LICENSE
MANIFEST.in
NOTICE
README.md
SECURITY.md
THIRD_PARTY_NOTICES.md
pyproject.toml
.github/workflows/ci.yml
.github/workflows/publish-images.yml
.github/workflows/release.yml
configs/apptainer-images.example.json
configs/assets.example.json
configs/assets.gated.example.json
configs/public-image-bases.json
configs/runtime.env.example
docker/core88_bigcodebench_sandbox.Dockerfile
docker/core88_ds1000.Dockerfile
docker/core88_sandbox.Dockerfile
docker/core88_thin_sandbox.Dockerfile
docker/offline-assets.Dockerfile
docker/runtime.Dockerfile
docs/IMAGES.md
docs/OFFLINE_ASSETS.md
docs/PORTABILITY.md
docs/PROTOCOLS.md
docs/RELEASE_CHECKLIST.md
docs/SPECULATIVE_DECODING.md
docs/VALIDATION.md
docs/validation/dflash_a14_synthetic.json
scripts/build-public-images.sh
scripts/render-kubernetes-jobs.py
scripts/run-plan-local.sh
scripts/run-task-apptainer.sh
scripts/submit-plan-slurm.sh
src/ncp_olmo_eval/__init__.py
src/ncp_olmo_eval/assets.py
src/ncp_olmo_eval/benchmark.py
src/ncp_olmo_eval/core88_workflow.py
src/ncp_olmo_eval/core_native_aggregate.py
src/ncp_olmo_eval/core_native_answer_eval.py
src/ncp_olmo_eval/core_native_cached_finalize.py
src/ncp_olmo_eval/core_native_code_eval.py
src/ncp_olmo_eval/core_native_contract.py
src/ncp_olmo_eval/core_native_eval.py
src/ncp_olmo_eval/core_native_plan.py
src/ncp_olmo_eval/core_native_pool.py
src/ncp_olmo_eval/core_native_summary.py
src/ncp_olmo_eval/core_native_work.py
src/ncp_olmo_eval/device_layout.py
src/ncp_olmo_eval/dflash_checkpoint.py
src/ncp_olmo_eval/dflash_contract.py
src/ncp_olmo_eval/evaluation_cli.py
src/ncp_olmo_eval/gsm8k_eval.py
src/ncp_olmo_eval/helmet_api_judge.py
src/ncp_olmo_eval/helmet_prepare.py
src/ncp_olmo_eval/helmet_protocol.py
src/ncp_olmo_eval/helmet_score.py
src/ncp_olmo_eval/helmet_trec_eval_compat.py
src/ncp_olmo_eval/inference.py
src/ncp_olmo_eval/lm_eval_runtime.py
src/ncp_olmo_eval/lmdeploy_inference.py
src/ncp_olmo_eval/long_context_inference.py
src/ncp_olmo_eval/long_context_prepare.py
src/ncp_olmo_eval/long_context_protocol.py
src/ncp_olmo_eval/long_context_score.py
src/ncp_olmo_eval/native_megatron_inference.py
src/ncp_olmo_eval/native_vllm_inference.py
src/ncp_olmo_eval/ncp_dflash_vllm_benchmark.py
src/ncp_olmo_eval/portable_tasks.py
src/ncp_olmo_eval/prepare_cli.py
src/ncp_olmo_eval/prepare_long_context_model_overlay.py
src/ncp_olmo_eval/prepare_native_vllm_model.py
src/ncp_olmo_eval/py.typed
src/ncp_olmo_eval/runtime_smoke.py
src/ncp_olmo_eval/source_identity.py
src/ncp_olmo_eval/task_runner.py
src/ncp_olmo_eval/task_spec.py
src/ncp_olmo_eval/transformers_inference.py
src/ncp_olmo_eval/unified_eval_results.py
src/ncp_olmo_eval.egg-info/PKG-INFO
src/ncp_olmo_eval.egg-info/SOURCES.txt
src/ncp_olmo_eval.egg-info/dependency_links.txt
src/ncp_olmo_eval.egg-info/entry_points.txt
src/ncp_olmo_eval.egg-info/requires.txt
src/ncp_olmo_eval.egg-info/top_level.txt
src/ncp_olmo_eval/vllm_plugin/__init__.py
src/ncp_olmo_eval/vllm_plugin/batch_invariance.py
src/ncp_olmo_eval/vllm_plugin/compare_backend_runs.py
src/ncp_olmo_eval/vllm_plugin/compare_flash_versions.py
src/ncp_olmo_eval/vllm_plugin/contract.py
src/ncp_olmo_eval/vllm_plugin/gsm8k.py
src/ncp_olmo_eval/vllm_plugin/hf_config.py
src/ncp_olmo_eval/vllm_plugin/hlm.py
src/ncp_olmo_eval/vllm_plugin/model.py
src/ncp_olmo_eval/vllm_plugin/model_runner.py
src/ncp_olmo_eval/vllm_plugin/ncp_dflash_proposer.py
src/ncp_olmo_eval/vllm_plugin/ncp_dflash_state.py
src/ncp_olmo_eval/vllm_plugin/parity.py
src/ncp_olmo_eval/vllm_plugin/plugin.py
src/ncp_olmo_eval/vllm_plugin/probe.py
src/ncp_olmo_eval/vllm_plugin/qkv.py
src/ncp_olmo_eval/vllm_plugin/routes.py
src/ncp_olmo_eval/vllm_plugin/state.py
src/ncp_olmo_eval/vllm_plugin/throughput.py
src/ncp_olmo_eval/vllm_plugin/token_tower.py
src/ncp_olmo_eval/vllm_plugin/weights.py
src/ncp_olmo_eval/vllm_plugin/worker.py
tests/conftest.py
tests/installed_package_summary_smoke.py
tests/unit/test_bigcodebench_sandbox_contract.py
tests/unit/test_core88_workflow.py
tests/unit/test_core_native_cached_finalize.py
tests/unit/test_core_native_code_loader.py
tests/unit/test_core_native_summary.py
tests/unit/test_core_summary_source_identity.py
tests/unit/test_dflash_checkpoint.py
tests/unit/test_dflash_contract.py
tests/unit/test_evaluation_cli.py
tests/unit/test_gsm8k_eval.py
tests/unit/test_helmet_api_judge.py
tests/unit/test_helmet_protocol.py
tests/unit/test_lm_eval_runtime.py
tests/unit/test_long_context_protocol.py
tests/unit/test_native_vllm_inference.py
tests/unit/test_ncp_dflash_vllm_benchmark.py
tests/unit/test_portable_runtime.py
tests/unit/test_release_integrity.py
tests/unit/test_release_metadata.py
tests/unit/test_sciq_protocol.py
tests/vllm_plugin/test_compare_backend_runs.py
tests/vllm_plugin/test_compare_flash_versions.py
tests/vllm_plugin/test_contract.py
tests/vllm_plugin/test_gsm8k.py
tests/vllm_plugin/test_hf_config.py
tests/vllm_plugin/test_hlm.py
tests/vllm_plugin/test_model_transaction.py
tests/vllm_plugin/test_ncp_dflash_model_runner.py
tests/vllm_plugin/test_ncp_dflash_proposer.py
tests/vllm_plugin/test_ncp_dflash_state.py
tests/vllm_plugin/test_plugin.py
tests/vllm_plugin/test_qk_norm.py
tests/vllm_plugin/test_state.py
tests/vllm_plugin/test_weights.py