Litgpt

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

What's Changed
* Apply prompt style for tp.py and sequentially.py by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1629
* Fix prompt docstring in Python API by rasbt in https://github.com/Lightning-AI/litgpt/pull/1635
* Update windows cpu-tests.yml by rasbt in https://github.com/Lightning-AI/litgpt/pull/1630
* Remove NumPy < 2.0 pin by rasbt in https://github.com/Lightning-AI/litgpt/pull/1631
* Fix kv-cache issue in Python API streaming mode by rasbt in https://github.com/Lightning-AI/litgpt/pull/1633
* Updates installation requirements to install minimal required packages for basic use by rasbt in https://github.com/Lightning-AI/litgpt/pull/1634
* Faster safetensors conversion when downloading model by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1624
* Add Sebastian as code owner by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1641
* Add missing super() call in data modules by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1639
* Update Lightning version to 2.4.0 pre by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1640
* Add tunable kvcache with error handling for nonsense inputs. by apaz-cli in https://github.com/Lightning-AI/litgpt/pull/1636
* Use Python API in serve code by rasbt in https://github.com/Lightning-AI/litgpt/pull/1644
* Fix autodownload + conversion issue by rasbt in https://github.com/Lightning-AI/litgpt/pull/1645
* Properly clear kv-cache by rasbt in https://github.com/Lightning-AI/litgpt/pull/1647
* Fix error raising where max_returned_tokens > max_seq_length_setting by rasbt in https://github.com/Lightning-AI/litgpt/pull/1648
* Add quantization support to litgpt serve by rasbt in https://github.com/Lightning-AI/litgpt/pull/1646
* Bump for 0.4.7 release by rasbt in https://github.com/Lightning-AI/litgpt/pull/1649


**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.6...v0.4.7

What's Changed
* Change default top_k to 50 everywhere for consistency by rasbt in https://github.com/Lightning-AI/litgpt/pull/1592
* Fix kv-cache clearing in Python API and Serve by rasbt in https://github.com/Lightning-AI/litgpt/pull/1596
* dynamic KV Cache batching by aniketmaurya in https://github.com/Lightning-AI/litgpt/pull/1600
* Remove non-used eos_id in Python API by rasbt in https://github.com/Lightning-AI/litgpt/pull/1594
* Add quantization test and revert lightning version by rasbt in https://github.com/Lightning-AI/litgpt/pull/1605
* Dynamically set kv-cache size in serve by rasbt in https://github.com/Lightning-AI/litgpt/pull/1602
* Update LitData version and restore previous LitData assertions in tests by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1609
* Gemma 2: `9b` and `27b` versions by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1545
* Update config hub table qlora sections by rasbt in https://github.com/Lightning-AI/litgpt/pull/1611
* max_returned_tokens -> max_new_tokens by rasbt in https://github.com/Lightning-AI/litgpt/pull/1612
* Add warning about pretrain preprocessing by rasbt in https://github.com/Lightning-AI/litgpt/pull/1618
* Print warning about unsupported repo_ids by rasbt in https://github.com/Lightning-AI/litgpt/pull/1617
* Restore capability to load alternative weights by rasbt in https://github.com/Lightning-AI/litgpt/pull/1620
* Enable unbalanced number of layers in sequential generation by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1623
* Llama 3.1 8B and 70B checkpoints by rasbt in https://github.com/Lightning-AI/litgpt/pull/1619
* Add Llama 3.1 405B config by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1622
* Bumb version to 0.4.6 for next release (Gemma 2 and Llama 3.1) by rasbt in https://github.com/Lightning-AI/litgpt/pull/1626


**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.5...v0.4.6

What's Changed
* Update LitData to latest version 0.2.16 by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1573
* Fixed warning during model download and conversion. by bhargavyagnik in https://github.com/Lightning-AI/litgpt/pull/1574
* Bump lightning version by awaelchli in https://github.com/Lightning-AI/litgpt/pull/1579
* chat/base.py: extend checkpoint_dir before accessing it by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1575
* Chat: dynamically set kv-cache size by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1583
* Add slow interconnect warning by rasbt in https://github.com/Lightning-AI/litgpt/pull/1577
* Mathstral checkpoints by rasbt in https://github.com/Lightning-AI/litgpt/pull/1587
* Make sure quantization is used correctly by rasbt in https://github.com/Lightning-AI/litgpt/pull/1585
* Improve mathstral tests by rasbt in https://github.com/Lightning-AI/litgpt/pull/1589
* Fixes an issue where the LitGPT Python API was consuming too much memory by rasbt in https://github.com/Lightning-AI/litgpt/pull/1590
* Increase version number for 0.4.5 release by rasbt in https://github.com/Lightning-AI/litgpt/pull/1591

New Contributors
* bhargavyagnik made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1574

**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.4...v0.4.5

What's Changed
* Tokenizer: fix issue when decoding a single token at a time by Andrei-Aksionov in https://github.com/Lightning-AI/litgpt/pull/1559
* Filter out false positive PyTorch scheduler warning by rasbt in https://github.com/Lightning-AI/litgpt/pull/1562
* Add an explanation on how to evaluate on a custom test set by rasbt in https://github.com/Lightning-AI/litgpt/pull/1564
* Remove duplicated bos_token for CodeLlama by alealv in https://github.com/Lightning-AI/litgpt/pull/1566
* Fix SFTDataset sample generation by alealv in https://github.com/Lightning-AI/litgpt/pull/1568
* Add Python API section to 0 to LitGPT docs by rasbt in https://github.com/Lightning-AI/litgpt/pull/1570
* Fix multi-turn prompting error handling and extra newline by apaz-cli in https://github.com/Lightning-AI/litgpt/pull/1569
* Add automatic downloading to CLI by rasbt in https://github.com/Lightning-AI/litgpt/pull/1571
* Bumb version for 0.4.4 release by rasbt in https://github.com/Lightning-AI/litgpt/pull/1572

New Contributors
* alealv made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1566
* apaz-cli made their first contribution in https://github.com/Lightning-AI/litgpt/pull/1569

**Full Changelog**: https://github.com/Lightning-AI/litgpt/compare/v0.4.3...v0.4.4