Leptonai

**Full Changelog**: https://github.com/leptonai/leptonai/compare/0.17.1...0.18.3

* feat(cli): add last modified time in object store by Yangqing in https://github.com/leptonai/leptonai/pull/359
* fix: run on_task in parallel with worker_max_concurrency by bddppq in https://github.com/leptonai/leptonai/pull/360
* feat(hf): automatically infer dependency from huggingface repo by Yangqing in https://github.com/leptonai/leptonai/pull/361
* fix(cli): fix job port bug by Yangqing in https://github.com/leptonai/leptonai/pull/362
* feat(cli): add a functionality to allow specifying additional dependencies by Yangqing in https://github.com/leptonai/leptonai/pull/363

* feat(sdk): add universal tokenizer readme by Yangqing in https://github.com/leptonai/leptonai/pull/352
* feat(hf): support token-classification by Yangqing in https://github.com/leptonai/leptonai/pull/355
* fix(hf): numpy only exists in runtime. by Yangqing in https://github.com/leptonai/leptonai/pull/357

* doc(worker): add doc for worker setup by bobmayuze in https://github.com/leptonai/leptonai/pull/349
* feat: update vllm photon to work with new version of vllm (0.3.3) by bddppq in https://github.com/leptonai/leptonai/pull/350

New Contributors
* axissun1 made their first contribution in https://github.com/leptonai/leptonai/pull/311
* AtomicVar made their first contribution in https://github.com/leptonai/leptonai/pull/315
* xudong963 made their first contribution in https://github.com/leptonai/leptonai/pull/317

**Full Changelog**: https://github.com/leptonai/leptonai/compare/0.16.0...0.17.1

* Update README: python -> Python by AtomicVar in https://github.com/leptonai/leptonai/pull/315
* docs: update templates doc by vthinkxie in https://github.com/leptonai/leptonai/pull/316
* chore: storrage to storage by xudong963 in https://github.com/leptonai/leptonai/pull/317
* Support specifying prompt length in benchmark by bddppq in https://github.com/leptonai/leptonai/pull/322
* fix(sdk): fix KV api json access by Yangqing in https://github.com/leptonai/leptonai/pull/326
* feat(sdk): make graceful timeout configurable by package-level defaults by Yangqing in https://github.com/leptonai/leptonai/pull/323
* fix(sdk): public photon deletion now supported. by Yangqing in https://github.com/leptonai/leptonai/pull/324
* feat(sdk): set graceful timeoout default for on-platform deployments by Yangqing in https://github.com/leptonai/leptonai/pull/327
* feat(job): complete the job arguments per the new spec. by Yangqing in https://github.com/leptonai/leptonai/pull/328
* fix(job): change cli entry to /bin/bash by bobmayuze in https://github.com/leptonai/leptonai/pull/329
* fix(whisperx): allow passing in empty string for language auto-detection, and keep default to English. by Yangqing in https://github.com/leptonai/leptonai/pull/330
* Revert "pre-install hf-transfer for faster download" by Yangqing in https://github.com/leptonai/leptonai/pull/331
* remove limits from python dep by bddppq in https://github.com/leptonai/leptonai/pull/333
* minor tuning of grace period param by Yangqing in https://github.com/leptonai/leptonai/pull/335