feat: add amd gpu llm recipes

[xieofxie]

revert of 21a3bad

[Copilot]

Pull request overview

This pull request adds AMD GPU (MIGraphX Execution Provider) support for four LLM models, reverting a previous removal of these configurations.

Changes:

• Adds MIGraphX execution provider configuration files for Phi-3.5-mini-instruct, Llama-3.2-1B-Instruct, DeepSeek-R1-Distill-Qwen-1.5B, and Qwen2.5-1.5B-Instruct models
• Updates documentation and metadata files to reflect AMD GPU runtime support for these models
• Configures copy rules to generate MIGraphX configs from existing DML configs

Reviewed changes

Copilot reviewed 23 out of 23 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
microsoft-Phi-3.5-mini-instruct/aitk/phi3_5_migraphx_config.json	MIGraphX runtime configuration for Phi-3.5 model with int4 precision
microsoft-Phi-3.5-mini-instruct/aitk/phi3_5_migraphx_config.json.config	UI metadata for MIGraphX config with AMD GPU display name
microsoft-Phi-3.5-mini-instruct/aitk/model_project.config	Registers MIGraphX template for Phi-3.5
microsoft-Phi-3.5-mini-instruct/aitk/info.yml	Adds MIGraphX recipe metadata
microsoft-Phi-3.5-mini-instruct/aitk/_copy.json.config	Defines copy rules to generate MIGraphX configs from DML configs
meta-llama-Llama-3.2-1B-Instruct/aitk/llama3_2_migraphx_config.json	MIGraphX runtime configuration for Llama 3.2 model
meta-llama-Llama-3.2-1B-Instruct/aitk/llama3_2_migraphx_config.json.config	UI metadata for Llama 3.2 MIGraphX config
meta-llama-Llama-3.2-1B-Instruct/aitk/model_project.config	Registers MIGraphX template for Llama 3.2
meta-llama-Llama-3.2-1B-Instruct/aitk/info.yml	Adds MIGraphX recipe metadata
meta-llama-Llama-3.2-1B-Instruct/aitk/_copy.json.config	Defines copy rules for Llama 3.2 MIGraphX configs
deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B/aitk/deepseek_migraphx_config.json	MIGraphX runtime configuration for DeepSeek model
deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B/aitk/deepseek_migraphx_config.json.config	UI metadata for DeepSeek MIGraphX config
deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B/aitk/model_project.config	Registers MIGraphX template for DeepSeek
deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B/aitk/info.yml	Adds MIGraphX recipe metadata
deepseek-ai-DeepSeek-R1-Distill-Qwen-1.5B/aitk/_copy.json.config	Defines copy rules for DeepSeek MIGraphX configs
Qwen-Qwen2.5-1.5B-Instruct/aitk/qwen2_5_migraphx_config.json	MIGraphX runtime configuration for Qwen 2.5 model
Qwen-Qwen2.5-1.5B-Instruct/aitk/qwen2_5_migraphx_config.json.config	UI metadata for Qwen 2.5 MIGraphX config
Qwen-Qwen2.5-1.5B-Instruct/aitk/model_project.config	Registers MIGraphX template for Qwen 2.5
Qwen-Qwen2.5-1.5B-Instruct/aitk/info.yml	Adds MIGraphX recipe metadata
Qwen-Qwen2.5-1.5B-Instruct/aitk/_copy.json.config	Defines copy rules for Qwen 2.5 MIGraphX configs
.aitk/docs/guide/ModelList.md	Updates model list documentation to include AMD GPU runtime links
.aitk/configs/model_list.json	Adds AMDGPU to runtime lists for the four models
.aitk/configs/checks.json	Updates validation checksums for new configuration files

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.