Fix issues in Llama-Cpp-Dockerfile and improve README instructions

[seshu1729]

Summary

This PR fixes issues in the Llama-Cpp-Dockerfile folder and updates the README to provide correct instructions for building and running the Docker container.

Changes

• Updated the Dockerfile to ensure the container builds successfully.
• Fixed configuration issues affecting the llama.cpp setup.
• Updated the README with clearer steps for building and running the Docker image.

Motivation

The existing Dockerfile and documentation in the Llama-Cpp-Dockerfile directory contained issues that prevented the container from building or running correctly.

This update aligns the Dockerfile and README with a working configuration so users can easily build and run the container.

How to Test

1. Navigate to the Llama-Cpp-Dockerfile directory.
2. Build the Docker Image

• Clone this repository and build the Docker image:

# Build the Docker image (replace <tag> with your preferred tag)
docker build -t llamacpp-intel-sycl:latest .

3. Run the Container

• To run the server with a default HuggingFace model (Qwen/Qwen2-0.5B-Instruct-GGUF):

# Default container
docker run -it --rm \
	--device /dev/dri \
	-p 8000:8000 \
	llamacpp-intel-sycl:latest

Impact

• Fixes Docker build issues.
• Improves usability for developers who want to run llama.cpp using Docker.

Checklist

• Docker image builds successfully
• README updated with correct instructions
• Tested locally
• No breaking changes
• Requires reviewer verification