# Next Steps

## In this learning path

- [Introduction](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_spark_llamacpp/)
- [Explore Grace Blackwell for quantized LLM inference](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_spark_llamacpp/1_gb10_introduction/)
- [Verify your Grace Blackwell system readiness for AI inference](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_spark_llamacpp/1a_gb10_setup/)
- [Build the GPU version of llama.cpp on GB10](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_spark_llamacpp/2_gb10_llamacpp_gpu/)
- [Build the CPU version of llama.cpp on GB10](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_spark_llamacpp/3_gb10_llamacpp_cpu/)
- [Analyze CPU instruction mix using Process Watch](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_spark_llamacpp/4_gb10_processwatch/)
- [Next Steps](https://learn.arm.com/learning-paths/laptops-and-desktops/dgx_spark_llamacpp/_next-steps/)

## Explore related resources
Find more information about the topics in this Learning Path:
- [NVIDIA DGX Spark website](https://www.nvidia.com/en-gb/products/workstations/dgx-spark/)
- [NVIDIA DGX Spark Playbooks GitHub repository](https://github.com/NVIDIA/dgx-spark-playbooks)
- [Profile llama.cpp performance with Arm Streamline and KleidiAI LLM kernels Learning Path](https://learn.arm.com/learning-paths/servers-and-cloud-computing/llama_cpp_streamline/)
- [Arm-Powered NVIDIA DGX Spark Workstations to Redefine AI](https://newsroom.arm.com/blog/arm-powered-nvidia-dgx-spark-ai-workstations)

## Review frequently asked questions
These FAQs were drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

### How do I know my DGX Spark is ready before building?
Confirm the Grace CPU configuration, operating system, Blackwell GPU, and CUDA drivers are active, and verify the CUDA 13 toolkit is installed.

### Which build should I start with, GPU-enabled or CPU-only?
If the Blackwell GPU and CUDA are available, start with the GPU-enabled `llama.cpp` build. Then, build the CPU-only version to run on the Grace CPU and to keep a flexible deployment option.

### What result should I expect after a successful build?
The build produces a compiled `llama.cpp` binary targeting either the GPU or the CPU that runs quantized LLM inference. A quick test run should complete without errors on the DGX Spark.

### How do I validate that the CPU-only build uses Armv9 vector features?
Run an inference with the CPU-only binary and analyze it with Process Watch to observe the instruction mix. Expect to see Neon SIMD activity; SVE and SVE2 might remain inactive under the current kernel configuration.

### Why don’t I see SVE or SVE2 instructions in my Process Watch results?
Although the Grace CPU supports SVE and SVE2, the current kernel exposes a fixed 16-byte (128-bit) SVE vector length. The `llama.cpp` workload therefore uses Neon instructions instead. Future kernel updates might enable SVE2 instructions.
