sarman/dgx-spark-playbooks
1
0
Fork 0
mirror of https://github.com/NVIDIA/dgx-spark-playbooks.git synced 2026-04-23 02:23:53 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
Collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices with Blackwell architecture.
176 Commits 1 Branch 0 Tags 59 MiB
Jupyter Notebook 69.4%
TypeScript 18.8%
Python 10.1%
CSS 0.8%
Shell 0.7%
23b5cbca4c
Go to file
Santosh Bhavani 23b5cbca4c feat(processor): add parallel processing and NVIDIA API support 
- Implement parallel chunk processing with configurable concurrency
- Add direct NVIDIA API integration bypassing LangChain for better control
- Optimize for DGX Spark unified memory with batch processing
- Use concurrency of 4 for Ollama, 2 for other providers
- Add proper error handling and user stop capability
- Update NVIDIA model to Llama 3.3 Nemotron Super 49B v1.5
- Improve prompt engineering for triple extraction
2025-10-19 20:58:59 -07:00
nvidia feat(processor): add parallel processing and NVIDIA API support 2025-10-19 20:58:59 -07:00
src/images chore: Regenerate all playbooks 2025-10-03 20:46:11 +00:00
LICENSE chore: Regenerate all playbooks 2025-10-03 20:46:11 +00:00
README.md chore: Regenerate all playbooks 2025-10-17 17:29:40 +00:00

README.md

NVIDIA DGX Spark

DGX Spark Playbooks

Collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices with Blackwell architecture.

About

These playbooks provide detailed instructions for:

  • Installing and configuring popular AI frameworks
  • Running inference with optimized models
  • Setting up development environments
  • Connecting and managing your DGX Spark device

Each playbook includes prerequisites, step-by-step instructions, troubleshooting guidance, and example code.

Available Playbooks

NVIDIA

Resources

License

See: