[SPARKNLP-1027] llama.cpp integration

[DevinTDHa]

Description

This PR implements support for llama.cpp in Spark NLP.

llama.cpp is a high-performance C/C++ library designed for running Meta's LLaMA models and other large language models (LLMs) on a variety of hardware platforms.

This will enable users to do inference of LLMs wich a variety of optimizations:

• Hardware Optimization: Supports Apple silicon via Metal, x86 architectures with AVX, NVIDIA GPUs (via CUDA).
• Quantization: Model Quantization (1.5-bit to 8-bit) to improve inference speed and reduce memory usage.

Motivation and Context

Many users will have clusters with many smaller nodes. This will enable these nodes to also perform inference for LLMs with limited memory.

How Has This Been Tested?

Local tests, google colab, databricks

Types of changes

• [ ] Bug fix (non-breaking change which fixes an issue)
• [ ] Code improvements with no or little impact
• [x] New feature (non-breaking change which adds functionality)
• [ ] Breaking change (fix or feature that would cause existing functionality to change)

Checklist:

• [x] My code follows the code style of this project.
• [x] My change requires a change to the documentation.
• [x] I have updated the documentation accordingly.
• [x] I have read the CONTRIBUTING page.
• [x] I have added tests to cover my changes.
• [x] All new and existing tests passed.

[coveralls]

Pull Request Test Coverage Report for Build 10718481706

Details

• 0 of 383 (0.0%) changed or added relevant lines in 2 files are covered.
• 49 unchanged lines in 33 files lost coverage.
• Overall coverage decreased (-1.6%) to 60.231%

---

Changes Missing Coverage	Covered Lines	Changed/Added Lines	%
src/main/scala/com/johnsnowlabs/nlp/pretrained/ResourceDownloader.scala	0	2	0.0%
src/main/scala/com/johnsnowlabs/nlp/HasLlamaCppProperties.scala	0	381	0.0%
<!--	Total:	0	383	0.0%	-->

Files with Coverage Reduction	New Missed Lines	%
src/main/scala/com/johnsnowlabs/nlp/annotators/DateMatcherTranslator.scala	1	89.35%
src/main/scala/com/johnsnowlabs/nlp/annotators/parser/dep/Tagger.scala	1	47.54%
src/main/scala/com/johnsnowlabs/nlp/annotators/ner/crf/FeatureGenerator.scala	1	94.41%
src/main/scala/com/johnsnowlabs/nlp/RawAnnotator.scala	1	80.0%
src/main/scala/com/johnsnowlabs/nlp/annotators/er/EntityRulerApproach.scala	1	95.11%
src/main/scala/com/johnsnowlabs/nlp/annotators/ner/dl/NerDLApproach.scala	1	80.0%
src/main/scala/com/johnsnowlabs/nlp/pretrained/ResourceDownloader.scala	1	41.04%
src/main/scala/com/johnsnowlabs/nlp/pretrained/S3ResourceDownloader.scala	1	52.59%
src/main/scala/com/johnsnowlabs/nlp/annotators/sda/vivekn/ViveknSentimentUtils.scala	1	52.94%
src/main/scala/com/johnsnowlabs/nlp/annotators/keyword/yake/YakeKeywordExtraction.scala	1	97.44%
<!--	Total:	49		-->

Totals
Change from base Build 10678787199:	-1.6%
Covered Lines:	8981
Relevant Lines:	14911

---

💛 - Coveralls