Deepspeed

What's Changed
* Update RESTful API by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/294
* Compatibility with DS Inference KV-cache flexibility PR by cmikeh2 in https://github.com/microsoft/DeepSpeed-MII/pull/284
* Use smaller model for unit tests by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/315
* Unify input/output types by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/295
* Multi-process RESTful API by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/328
* Add support for zero shot image classification task by PhaniShekhar in https://github.com/microsoft/DeepSpeed-MII/pull/326
* Add safetensors support by jihnenglin in https://github.com/microsoft/DeepSpeed-MII/pull/296
* Handling of edge case for text to image model by gauravrajguru in https://github.com/microsoft/DeepSpeed-MII/pull/334
* fix PR creation in release workflow by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/337

New Contributors
* cmikeh2 made their first contribution in https://github.com/microsoft/DeepSpeed-MII/pull/284
* PhaniShekhar made their first contribution in https://github.com/microsoft/DeepSpeed-MII/pull/326
* jihnenglin made their first contribution in https://github.com/microsoft/DeepSpeed-MII/pull/296

**Full Changelog**: https://github.com/microsoft/DeepSpeed-MII/compare/v0.1.1...v0.1.2

What's Changed
* Add MII v0.1 unit tests by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/262
* diffuser model load using model and path params by gauravrajguru in https://github.com/microsoft/DeepSpeed-MII/pull/264
* Reorganize code structure, fix client import bug by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/269
* Mitigate the risk of deadlock by tohtana in https://github.com/microsoft/DeepSpeed-MII/pull/274
* Expose top-p, top-k, and temperature to generate APIs by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/268
* Fix typo in README.md by eltociear in https://github.com/microsoft/DeepSpeed-MII/pull/259
* Enable multi-prompt input for persistent deployments by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/275
* Recompute when the deadlock is detected by tohtana in https://github.com/microsoft/DeepSpeed-MII/pull/278
* prevent load_with_sys_mem when using stable diffusion by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/279
* Add more generate() kwargs by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/280

New Contributors
* gauravrajguru made their first contribution in https://github.com/microsoft/DeepSpeed-MII/pull/264
* eltociear made their first contribution in https://github.com/microsoft/DeepSpeed-MII/pull/259

**Full Changelog**: https://github.com/microsoft/DeepSpeed-MII/compare/v0.1.0...v0.1.1

Features
* Distributed Training with Mixed Precision
* 16-bit mixed precision
* Single-GPU/Multi-GPU/Multi-Node
* Model Parallelism
* Support for Custom Model Parallelism
* Integration with Megatron-LM
* Memory and Bandwidth Optimizations
* Zero Redundancy Optimizer (ZeRO) stage 1 with all-reduce
* Constant Buffer Optimization (CBO)
* Smart Gradient Accumulation
* Training Features
* Simplified training API
* Gradient Clipping
* Automatic loss scaling with mixed precision
* Training Optimizers
* Fused Adam optimizer and arbitrary torch.optim.Optimizer
* Memory bandwidth optimized FP16 Optimizer
* Large Batch Training with LAMB Optimizer
* Memory efficient Training with ZeRO Optimizer
* Training Agnostic Checkpointing
* Advanced Parameter Search
* Learning Rate Range Test
* 1Cycle Learning Rate Schedule
* Simplified Data Loader
* Performance Analysis and Debugging

What's Changed
* Update version.txt after 0.0.8 release by loadams in https://github.com/microsoft/DeepSpeed-MII/pull/246
* Introduce pydantic_v1 compatibility module for pydantic>=2.0.0 support by ringohoffman in https://github.com/microsoft/DeepSpeed-MII/pull/240
* Improved the code quality to ease future maintenance by blackmambaza in https://github.com/microsoft/DeepSpeed-MII/pull/248

New Contributors
* ringohoffman made their first contribution in https://github.com/microsoft/DeepSpeed-MII/pull/240
* blackmambaza made their first contribution in https://github.com/microsoft/DeepSpeed-MII/pull/248

**Full Changelog**: https://github.com/microsoft/DeepSpeed-MII/compare/v0.0.8...v0.0.9

What's Changed
* Fixes for AML metatensor loading by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/244
* Update autoPR creation in release script by loadams in https://github.com/microsoft/DeepSpeed-MII/pull/245

New Contributors
* loadams made their first contribution in https://github.com/microsoft/DeepSpeed-MII/pull/245

**Full Changelog**: https://github.com/microsoft/DeepSpeed-MII/compare/v0.0.7...v0.0.8

What's Changed
* Cache HF API results by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/233
* Refactor Configs by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/218
* Re-enable non persistent test cases by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/238
* Add PyPI release workflow by mrwyattii in https://github.com/microsoft/DeepSpeed-MII/pull/239


**Full Changelog**: https://github.com/microsoft/DeepSpeed-MII/compare/v0.0.6...v0.0.7