Litgpt

What's Changed
* Make 0.4.13.dev1 version by rasbt in https://github.com/Lightning-AI/litgpt/pull/1722
* Enable MPS support for LitGPT by rasbt in https://github.com/Lightning-AI/litgpt/pull/1724
* Simplify MPS support by rasbt in https://github.com/Lightning-AI/litgpt/pull/1726
* Add Chainlit Studio by rasbt in https://github.com/Lightning-AI/litgpt/pull/1728
* Fixing the tokenizer for slimpajama data preparation by tomaslaz in https://github.com/Lightning-AI/litgpt/pull/1734
* Add pretrain conversion by rasbt in https://github.com/Lightning-AI/litgpt/pull/1735
* Typo fix and formatting improvements in API Trainer docs by rasbt in https://github.com/Lightning-AI/litgpt/pull/1736
* bump macos to m1 by t-vi in https://github.com/Lightning-AI/litgpt/pull/1725
* Improve filepath handling in unit tests by rasbt in https://github.com/Lightning-AI/litgpt/pull/1737
* Add a more informative message in case text exceeds context size by rasbt in https://github.com/Lightning-AI/litgpt/pull/1738
* Update Thunder README.md by rasbt in https://github.com/Lightning-AI/litgpt/pull/1740
* Add sliding window attention to Mistral and Phi 3 by rasbt in https://github.com/Lightning-AI/litgpt/pull/1741
* Extend context length for sliding window tests by rasbt in https://github.com/Lightning-AI/litgpt/pull/1742
* Fix jsonarparse version by rasbt in https://github.com/Lightning-AI/litgpt/pull/1748
* Update RoPE tests by rasbt in https://github.com/Lightning-AI/litgpt/pull/1746
* Make json parsing more robust by rasbt in https://github.com/Lightning-AI/litgpt/pull/1749
* Support for optimizers which don't have "fused" parameter such as grokadamw and 8bit bnb by mtasic85 in https://github.com/Lightning-AI/litgpt/pull/1744
* Increase rtol and atol in Gemma 2 for macOS by rasbt in https://github.com/Lightning-AI/litgpt/pull/1751
* Repair json files by rasbt in https://github.com/Lightning-AI/litgpt/pull/1752
* Llama 3.2 weights by rasbt in https://github.com/Lightning-AI/litgpt/pull/1750
* Bump version to 0.4.13 for new release by rasbt in https://github.com/Lightning-AI/litgpt/pull/1753
* Temporarily take out thunder dependency for deployment by rasbt in https://github.com/Lightning-AI/litgpt/pull/1754

New Contributors
* tomaslaz made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1734
* mtasic85 made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1744

**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.12...v0.4.13

What's Changed
* Preserve eos in encoding when max_seq_length = -1 by sanderland in https://github.com/Lightning-AI/litgpt/pull/1694
* Add `batched_next_token()` and `batched_sample()` by apaz-cli in https://github.com/Lightning-AI/litgpt/pull/1693
* bump thunder dependency to main by t-vi in https://github.com/Lightning-AI/litgpt/pull/1701
* add support for batched input_pos to model by t-vi in https://github.com/Lightning-AI/litgpt/pull/1700
* Add `batched_generate_fn()` by apaz-cli in https://github.com/Lightning-AI/litgpt/pull/1702
* minor Readme update/typos by Borda in https://github.com/Lightning-AI/litgpt/pull/1710
* Fix device Error in Decode Stream by Motsepe-Jr in https://github.com/Lightning-AI/litgpt/pull/1707
* Temporarily remove MPS device support by rasbt in https://github.com/Lightning-AI/litgpt/pull/1718
* Add uvloop as a dependency by rasbt in https://github.com/Lightning-AI/litgpt/pull/1719
* Change default precision on macOS by rasbt in https://github.com/Lightning-AI/litgpt/pull/1720
* Bump for v0.4.12 by rasbt in https://github.com/Lightning-AI/litgpt/pull/1721

New Contributors
* Motsepe-Jr made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1707

**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.11...v0.4.12

What's Changed
* Add distribute=None to python-api.md by rasbt in https://github.com/Lightning-AI/litgpt/pull/1676
* Make LitGPT LLM API compatible with PyTorch Lightning Trainer 1/2 by rasbt in https://github.com/Lightning-AI/litgpt/pull/1667
* Auto device handling in LLM API by rasbt in https://github.com/Lightning-AI/litgpt/pull/1677
* Fix KV cache issue in LLM API by rasbt in https://github.com/Lightning-AI/litgpt/pull/1678
* Improved benchmark utils by rasbt in https://github.com/Lightning-AI/litgpt/pull/1679
* Add PR benchmark util for internal use by rasbt in https://github.com/Lightning-AI/litgpt/pull/1680
* Added git hash to benchmark utility. by apaz-cli in https://github.com/Lightning-AI/litgpt/pull/1681
* Spelling fix by rasbt in https://github.com/Lightning-AI/litgpt/pull/1685
* Add Microsoft Phi 3.5 checkpoint by rasbt in https://github.com/Lightning-AI/litgpt/pull/1687
* Update check_nvlink_connectivity by sanderland in https://github.com/Lightning-AI/litgpt/pull/1684
* Make number of generated tokens consistent with CLI by rasbt in https://github.com/Lightning-AI/litgpt/pull/1690
* Avoid error when executing benchmark util outside a git folder by rasbt in https://github.com/Lightning-AI/litgpt/pull/1691
* Combine `generate()` functions by apaz-cli in https://github.com/Lightning-AI/litgpt/pull/1675
* Bumb version to 0.4.11 by rasbt in https://github.com/Lightning-AI/litgpt/pull/1695
* Fix falcon prompt template by rasbt in https://github.com/Lightning-AI/litgpt/pull/1696

New Contributors
* sanderland made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1684

**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.10...v0.4.11

What's Changed
* Support Tensor Parallel in Python API by rasbt in https://github.com/Lightning-AI/litgpt/pull/1661
* Swap old Llama model with Phi-3 by rasbt in https://github.com/Lightning-AI/litgpt/pull/1666
* Update azure-gpu-test.yml by rasbt in https://github.com/Lightning-AI/litgpt/pull/1669
* Support the refactored API in litgpt serve by rasbt in https://github.com/Lightning-AI/litgpt/pull/1668
* Multi-gpu serving by rasbt in https://github.com/Lightning-AI/litgpt/pull/1670
* Add Mistral Large 123B by rasbt in https://github.com/Lightning-AI/litgpt/pull/1673
* Bumb version to 0.4.10 for next release by rasbt in https://github.com/Lightning-AI/litgpt/pull/1674


**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.9...v0.4.10

What's Changed

* Update LitServe version and tests by rasbt in https://github.com/Lightning-AI/litgpt/pull/1654
* Support for using large models in the Python API via sequential generation by rasbt in https://github.com/Lightning-AI/litgpt/pull/1637
* Add a PyTorch Lightning example by rasbt in https://github.com/Lightning-AI/litgpt/pull/1656
* Refactor Python API to introduce new distribute method (part of a larger refactor for PTL support) by rasbt in https://github.com/Lightning-AI/litgpt/pull/1657
* Fix some issues with circular and relative imports by rasbt in https://github.com/Lightning-AI/litgpt/pull/1658
* Optionally return benchmark info in Python API by rasbt in https://github.com/Lightning-AI/litgpt/pull/1660
* Bumb version for 0.4.9 release by rasbt in https://github.com/Lightning-AI/litgpt/pull/1664


**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.8...v0.4.9

What's Changed
* Adds unit test to test for parity between streaming and non-streaming API by rasbt in https://github.com/Lightning-AI/litgpt/pull/1650
* Add Gemma 2 2B by rasbt in https://github.com/Lightning-AI/litgpt/pull/1651
* Pin litserve version by rasbt in https://github.com/Lightning-AI/litgpt/pull/1652
* Version bumb for Gemma 2 2B release by rasbt in https://github.com/Lightning-AI/litgpt/pull/1653


**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.7...v0.4.8