Is your feature request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

Describe the solution you'd like
The GenAI packages will provide torchsharp implementation for a series of popular GenAI models. The goal is to load the same weight from the corresponding python regular model.

• Add design doc (add document for GenAI #7170)
• Add Microsoft.ML.GenAI.Core (Add GenAI core package #7177)

The following models will be added in the first wave

• Phi-3 (Microsoft.ML.GenAI.Phi) Add Microsoft.ML.GenAI.Phi, test package and sample project. #7184
  • Add README to Microsoft.ML.GenAI.Phi project [GenAI] Add readme to Microsoft.ML.GenAI.Phi #7206
• LLaMA (Microsoft.ML.GenAI.LLaMA) [GenAI] Add LLaMA support #7220
• Mistral (Microsoft.ML.GenAI.Mistral)
  • Mistral-7b-instruct v3
  • Mistral-nemo
• Generate Embedding from CausalLMModel [GenAI] Add generateEmbedding API to CausalLMPipeline #7227
• Stable Diffusion (Microsoft.ML.GenAI.StableDiffusion)

MEAI intergration

• Add CausalLMPipelineChatClient [GenAI] Introduce CausalLMPipelineChatClient for MEAI.IChatClient #7270

Along with the benchmark

• Benchmark for Phi-3

• Flash Attention support [GenAI] Add FlashAttention #7238

Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.

Additional context
Add any other context or screenshots about the feature request here.