NVIDIA/cloudai v1.7.0-1

v1.7.0-1

Repository: NVIDIA/cloudai

Tag: v1.7.0-1

Published: 2026-06-05T07:26:01Z

Prerelease: yes

Release notes:

What's Changed

• Installables: allow custom ones by @podkidyshev in https://github.com/NVIDIA/cloudai/pull/885
• NIXL EP: add single sbatch support by @podkidyshev in https://github.com/NVIDIA/cloudai/pull/889
• Append trajectory row on cache hits by @rutayan-nv in https://github.com/NVIDIA/cloudai/pull/888
• Ipod/custom srun bash by @podkidyshev in https://github.com/NVIDIA/cloudai/pull/896
• [Configurator] Make select_action observation-aware by @rutayan-nv in https://github.com/NVIDIA/cloudai/pull/892
• feat(dynamo_mocker): add GPU-free LLM inference simulation workload by @saivishal1999 in https://github.com/NVIDIA/cloudai/pull/895
• Bump idna from 3.11 to 3.15 by @dependabot[bot] in https://github.com/NVIDIA/cloudai/pull/897
• Bump python-dotenv from 1.2.1 to 1.2.2 by @dependabot[bot] in https://github.com/NVIDIA/cloudai/pull/878
• Bump urllib3 from 2.6.3 to 2.7.0 by @dependabot[bot] in https://github.com/NVIDIA/cloudai/pull/887
• vLLM/SGLANG: add semantic degradation support by @podkidyshev in https://github.com/NVIDIA/cloudai/pull/890
• feat(ai_dynamo): add aiperf workload support by @saivishal1999 in https://github.com/NVIDIA/cloudai/pull/898
• AIDynamo: add semantic degradation evaluation support by @podkidyshev in https://github.com/NVIDIA/cloudai/pull/903
• AIDynamo: enable LMCache by @podkidyshev in https://github.com/NVIDIA/cloudai/pull/906
• AIDynamo: enable multiple AIPerf runs during a single test run by @podkidyshev in https://github.com/NVIDIA/cloudai/pull/907
• AIDynamo: Optional restart of DynamoRouter between AIPerf re-runs by @podkidyshev in https://github.com/NVIDIA/cloudai/pull/908
• AIDynamo: shared node disagg inference by @podkidyshev in https://github.com/NVIDIA/cloudai/pull/909
• vLLM/SGLang: comparison report by @podkidyshev in https://github.com/NVIDIA/cloudai/pull/904
• NIXL EP: comparison report by @podkidyshev in https://github.com/NVIDIA/cloudai/pull/911

New Contributors

• @saivishal1999 made their first contribution in https://github.com/NVIDIA/cloudai/pull/895

Full Changelog: https://github.com/NVIDIA/cloudai/compare/v1.6.1...v1.7.0-1