Merge branch 'main' into rlm/update-readme-langchain-agents

docs/multi_gpu.md

docs/single_gpu.md

recipes/README.md

.../inference_throughput/on-prem/vllm/chat_vllm_benchmark.py

...chmarks/inference_throughput/on-prem/vllm/parameters.json

...ence_throughput/on-prem/vllm/pretrained_vllm_benchmark.py

recipes/finetuning/README.md

recipes/finetuning/multigpu_finetuning.md

recipes/finetuning/singlegpu_finetuning.md

recipes/inference/llama_web_ui/Llama2_Gradio.ipynb

recipes/inference/llama_web_ui/README.md

recipes/inference/llama_web_ui/requirements.txt

recipes/inference/llama_web_ui/streamlit_llama2.py

recipes/inference/local_inference/README.md

recipes/inference/model_servers/README.md

...a_api_providers/Azure_API_example/azure_api_example.ipynb

recipes/use_cases/MediaGen.ipynb

recipes/use_cases/README.md

..._cases/chatbots/sales_bot/Musical_instruments_reviews.csv

recipes/use_cases/chatbots/sales_bot/SalesBot.ipynb