Optimum-Nvidia v0.1.0 Beta 8

Highlight

• Exporting a model is now more robust and better defined overall compared to previous version. All the parameters are now exposed through optimum.nvidia.ExportConfig
• Bring back quantization and sparsity through integration of Nvidia's ModelOpt
• Added examples of quantization and sparsification recipes under examples/quantization
• Integrated optimum-nvidia with the latest optimum-cli interface to support exporting engines without any code through optimum-cli export trtllm.

Known Issues

• ModelOpt v0.15 as integrated in optimum-nvidia has an issue when trying to quantize with AWQ schema which is gone with v0.17. This dependency will be upgraded in the next release

What's Changed

• feat(package): make sure we dont have init as optimum level by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/132
• Enable trufflehog scanner CI on GA by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/136
• Enable automatic build of container at each release by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/137
• Refactor the overall Hugging Face -> TRTLLM export workflow by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/133
• feat(tests) : Update CI to use new workflow and silicon. by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/145
• move to new cluster by @glegendre01 in https://github.com/huggingface/optimum-nvidia/pull/150
• Bring back quantization with Nvidia ModelOpt by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/147
• (misc) disable xQA kernels for now as they seem to hang by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/152
• Add CLI quantization option by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/153
• tests(cli): uncomment out tests for CLI by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/154
• Fix license detection path by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/155
• Fix test again by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/156
• chore: remove invalid examples by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/157
• Bump version to 0.1.0b8 by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/158
• chore: update README badges by @mfuntowicz in https://github.com/huggingface/optimum-nvidia/pull/159

Full Changelog: https://github.com/huggingface/optimum-nvidia/compare/v0.1.0b7...v0.1.0b8