CHANGELOG.md
CITATION.cff
CODE_OF_CONDUCT.md
CONTRIBUTING.md
LICENSE
MANIFEST.in
README.md
SECURITY.md
STATUS.md
SUPPORT.md
pyproject.toml
docs/PRODUCT.md
docs/benchmark-format.md
docs/benchmark-reliability-52630.md
docs/example-reports.md
docs/experiment-log.md
docs/gate-calibration.md
docs/github-actions.md
docs/input-formats.md
docs/local-integration.md
docs/measurement-quality.md
docs/upgrade-guard.md
docs/validation-vllm-52630.md
docs/assets/banner.svg
docs/assets/decision.svg
docs/assets/terminal.svg
examples/inference-ci-reliability-001/README.md
examples/inference-ci-reliability-001/summary.json
examples/inference-ci-reliability-001/baseline/repetition-001.json
examples/inference-ci-reliability-001/baseline/repetition-002.json
examples/inference-ci-reliability-001/baseline/repetition-003.json
examples/inference-ci-reliability-001/baseline/repetition-004.json
examples/inference-ci-reliability-001/baseline/repetition-005.json
examples/inference-ci-reliability-001/baseline/repetition-006.json
examples/inference-ci-reliability-001/candidate/repetition-001.json
examples/inference-ci-reliability-001/candidate/repetition-002.json
examples/inference-ci-reliability-001/candidate/repetition-003.json
examples/inference-ci-reliability-001/candidate/repetition-004.json
examples/inference-ci-reliability-001/candidate/repetition-005.json
examples/inference-ci-reliability-001/candidate/repetition-006.json
examples/quickstart/README.md
examples/quickstart/baseline/repetition-001.json
examples/quickstart/baseline/repetition-002.json
examples/quickstart/baseline/repetition-003.json
examples/quickstart/baseline/repetition-004.json
examples/quickstart/baseline/repetition-005.json
examples/quickstart/candidate/repetition-001.json
examples/quickstart/candidate/repetition-002.json
examples/quickstart/candidate/repetition-003.json
examples/quickstart/candidate/repetition-004.json
examples/quickstart/candidate/repetition-005.json
examples/quickstart/regressed-candidate/repetition-001.json
examples/quickstart/regressed-candidate/repetition-002.json
examples/quickstart/regressed-candidate/repetition-003.json
examples/quickstart/regressed-candidate/repetition-004.json
examples/quickstart/regressed-candidate/repetition-005.json
examples/vllm-bench-serve/README.md
examples/vllm-bench-serve/baseline/openai-chat-infqps-concurrency64-Llama-3.1-8B-Instruct-20261011-100000.json
examples/vllm-bench-serve/baseline/openai-chat-infqps-concurrency64-Llama-3.1-8B-Instruct-20261011-110000.json
examples/vllm-bench-serve/baseline/openai-chat-infqps-concurrency64-Llama-3.1-8B-Instruct-20261011-120000.json
examples/vllm-bench-serve/baseline/openai-chat-infqps-concurrency64-Llama-3.1-8B-Instruct-20261011-130000.json
examples/vllm-bench-serve/baseline/openai-chat-infqps-concurrency64-Llama-3.1-8B-Instruct-20261011-140000.json
examples/vllm-bench-serve/candidate/openai-chat-infqps-concurrency64-Llama-3.1-8B-Instruct-20261011-100000.json
examples/vllm-bench-serve/candidate/openai-chat-infqps-concurrency64-Llama-3.1-8B-Instruct-20261011-110000.json
examples/vllm-bench-serve/candidate/openai-chat-infqps-concurrency64-Llama-3.1-8B-Instruct-20261011-120000.json
examples/vllm-bench-serve/candidate/openai-chat-infqps-concurrency64-Llama-3.1-8B-Instruct-20261011-130000.json
examples/vllm-bench-serve/candidate/openai-chat-infqps-concurrency64-Llama-3.1-8B-Instruct-20261011-140000.json
experiments/inference-ci-reliability-001/README.md
experiments/inference-ci-reliability-001/__init__.py
experiments/inference-ci-reliability-001/analysis.py
experiments/inference-ci-reliability-001/benchmark_block.py
experiments/inference-ci-reliability-001/common.py
experiments/inference-ci-reliability-001/experiment.json
experiments/inference-ci-reliability-001/run_experiment.py
experiments/vllm-48035/README.md
experiments/vllm-48035/RUNPOD.md
experiments/vllm-48035/aggregate.py
experiments/vllm-48035/benchmark_client.py
experiments/vllm-48035/compare_results.py
experiments/vllm-48035/experiment.json
experiments/vllm-48035/harness_common.py
experiments/vllm-48035/prompts.json
experiments/vllm-48035/run_experiment.py
experiments/vllm-52630/README.md
experiments/vllm-52630/RUNPOD.md
experiments/vllm-52630/aggregate.py
experiments/vllm-52630/benchmark_pooling.py
experiments/vllm-52630/compare_results.py
experiments/vllm-52630/dataset_manifest.json
experiments/vllm-52630/experiment.json
experiments/vllm-52630/harness_common.py
experiments/vllm-52630/run_same_gpu.py
src/inference_doctor/__init__.py
src/inference_doctor/__main__.py
src/inference_doctor/adapters.py
src/inference_doctor/benchmark_results.py
src/inference_doctor/cli.py
src/inference_doctor/comparison.py
src/inference_doctor/comparison_report.py
src/inference_doctor/diagnostics.py
src/inference_doctor/models.py
src/inference_doctor/quality.py
src/inference_doctor/quality_report.py
src/inference_doctor/report.py
src/inference_doctor/stats.py
src/inference_doctor/telemetry.py
src/inference_doctor.egg-info/PKG-INFO
src/inference_doctor.egg-info/SOURCES.txt
src/inference_doctor.egg-info/dependency_links.txt
src/inference_doctor.egg-info/entry_points.txt
src/inference_doctor.egg-info/requires.txt
src/inference_doctor.egg-info/top_level.txt
src/inference_doctor/collectors/__init__.py
src/inference_doctor/collectors/prometheus.py
tests/conftest.py
tests/test_adapters.py
tests/test_cli.py
tests/test_compare.py
tests/test_diagnostics.py
tests/test_gate.py
tests/test_inference_ci_reliability.py
tests/test_inputs.py
tests/test_multi_metric.py
tests/test_quality.py
tests/test_validation_52630.py
tests/test_vllm_48035_harness.py
tests/test_vllm_52630_harness.py
tests/fixtures/compare/baseline.json
tests/fixtures/compare/candidate_28pct_regression.json
tools/gate_simulation.py
tools/render_readme_media.py
tools/validate_vllm_52630.py